Upload folder using huggingface_hub

ft_7b_NLSY79_with_birth_year_ckpt_3/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_with_birth_year_ckpt_3/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_with_birth_year_ckpt_3/model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea3c38ad12f3c6de8667ae651607418699e48c9f24788bf8537963ca4601e853
+size 4840396416

ft_7b_NLSY79_with_birth_year_ckpt_3/model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b99160d884f977dc2ae52b6adda4337eb6a485af183cce2018f3e9b974033f6
+size 4857206856

ft_7b_NLSY79_with_birth_year_ckpt_3/model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a44fcddc3bc050fb5bb26df83952b1050f54d126739e738be08f3f7939c51613
+size 4857206904

ft_7b_NLSY79_with_birth_year_ckpt_3/model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:996568029e9eb56edb71d8656b90bc8062dca3f38f1649ef984f04a77db9f144
+size 4857206904

ft_7b_NLSY79_with_birth_year_ckpt_3/model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fa27406b8b3bbf373944d41c73fd9e3f3bd9bed8c0551c5798f9e04c6706411
+size 4857206904

ft_7b_NLSY79_with_birth_year_ckpt_3/model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:993a15737f4f6b83f78aa90c086cf7b5f878b3583808e2cd60b33c42706b6f31
+size 2684472112

ft_7b_NLSY79_with_birth_year_ckpt_3/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_with_birth_year_ckpt_3/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_with_birth_year_ckpt_3/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_with_birth_year_ckpt_3/trainer_state.json

@@ -0,0 +1,687 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 30,
+  "global_step": 90,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 11.47381591796875,
+      "learning_rate": 9.88888888888889e-06,
+      "loss": 0.9256,
+      "step": 1
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 5.464111804962158,
+      "learning_rate": 9.777777777777779e-06,
+      "loss": 0.7877,
+      "step": 2
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.034327030181885,
+      "learning_rate": 9.666666666666667e-06,
+      "loss": 0.4529,
+      "step": 3
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 6.164551734924316,
+      "learning_rate": 9.555555555555556e-06,
+      "loss": 0.3675,
+      "step": 4
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 3.3634986877441406,
+      "learning_rate": 9.444444444444445e-06,
+      "loss": 0.2255,
+      "step": 5
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.7426445484161377,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 0.2054,
+      "step": 6
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 0.8160797953605652,
+      "learning_rate": 9.222222222222224e-06,
+      "loss": 0.1751,
+      "step": 7
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.5050817728042603,
+      "learning_rate": 9.111111111111112e-06,
+      "loss": 0.1719,
+      "step": 8
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.6005658507347107,
+      "learning_rate": 9e-06,
+      "loss": 0.1729,
+      "step": 9
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.4815045893192291,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.1671,
+      "step": 10
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 0.3993792235851288,
+      "learning_rate": 8.777777777777778e-06,
+      "loss": 0.1536,
+      "step": 11
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.3682823181152344,
+      "learning_rate": 8.666666666666668e-06,
+      "loss": 0.1524,
+      "step": 12
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 0.375742644071579,
+      "learning_rate": 8.555555555555556e-06,
+      "loss": 0.153,
+      "step": 13
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.3199913501739502,
+      "learning_rate": 8.444444444444446e-06,
+      "loss": 0.1489,
+      "step": 14
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.38404566049575806,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.1496,
+      "step": 15
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.2665367126464844,
+      "learning_rate": 8.222222222222222e-06,
+      "loss": 0.1461,
+      "step": 16
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 0.2858336269855499,
+      "learning_rate": 8.111111111111112e-06,
+      "loss": 0.1493,
+      "step": 17
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.5412737727165222,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.1496,
+      "step": 18
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 0.29392877221107483,
+      "learning_rate": 7.88888888888889e-06,
+      "loss": 0.1428,
+      "step": 19
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.2921103835105896,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 0.143,
+      "step": 20
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.3292021155357361,
+      "learning_rate": 7.666666666666667e-06,
+      "loss": 0.1422,
+      "step": 21
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.2473241686820984,
+      "learning_rate": 7.555555555555556e-06,
+      "loss": 0.1414,
+      "step": 22
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 0.2409202605485916,
+      "learning_rate": 7.444444444444445e-06,
+      "loss": 0.1433,
+      "step": 23
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.2560567557811737,
+      "learning_rate": 7.333333333333333e-06,
+      "loss": 0.1369,
+      "step": 24
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.24865545332431793,
+      "learning_rate": 7.222222222222223e-06,
+      "loss": 0.1412,
+      "step": 25
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.20426170527935028,
+      "learning_rate": 7.111111111111112e-06,
+      "loss": 0.1426,
+      "step": 26
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.27498379349708557,
+      "learning_rate": 7e-06,
+      "loss": 0.1468,
+      "step": 27
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.2349638193845749,
+      "learning_rate": 6.88888888888889e-06,
+      "loss": 0.1449,
+      "step": 28
+    },
+    {
+      "epoch": 0.9666666666666667,
+      "grad_norm": 0.1899290233850479,
+      "learning_rate": 6.777777777777779e-06,
+      "loss": 0.1378,
+      "step": 29
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.319358229637146,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.1367,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.13972802460193634,
+      "eval_runtime": 2.659,
+      "eval_samples_per_second": 50.019,
+      "eval_steps_per_second": 1.88,
+      "step": 30
+    },
+    {
+      "epoch": 1.0333333333333334,
+      "grad_norm": 0.21085387468338013,
+      "learning_rate": 6.555555555555556e-06,
+      "loss": 0.142,
+      "step": 31
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.22181034088134766,
+      "learning_rate": 6.444444444444445e-06,
+      "loss": 0.1299,
+      "step": 32
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.23821492493152618,
+      "learning_rate": 6.333333333333333e-06,
+      "loss": 0.1325,
+      "step": 33
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.26432767510414124,
+      "learning_rate": 6.222222222222223e-06,
+      "loss": 0.143,
+      "step": 34
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.3544078469276428,
+      "learning_rate": 6.111111111111112e-06,
+      "loss": 0.143,
+      "step": 35
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.3023113012313843,
+      "learning_rate": 6e-06,
+      "loss": 0.1425,
+      "step": 36
+    },
+    {
+      "epoch": 1.2333333333333334,
+      "grad_norm": 0.17861610651016235,
+      "learning_rate": 5.88888888888889e-06,
+      "loss": 0.1413,
+      "step": 37
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.25699499249458313,
+      "learning_rate": 5.777777777777778e-06,
+      "loss": 0.1393,
+      "step": 38
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.18591469526290894,
+      "learning_rate": 5.666666666666667e-06,
+      "loss": 0.1352,
+      "step": 39
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.21023885905742645,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 0.1352,
+      "step": 40
+    },
+    {
+      "epoch": 1.3666666666666667,
+      "grad_norm": 0.1967165768146515,
+      "learning_rate": 5.444444444444445e-06,
+      "loss": 0.141,
+      "step": 41
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.21202944219112396,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 0.1396,
+      "step": 42
+    },
+    {
+      "epoch": 1.4333333333333333,
+      "grad_norm": 0.18353505432605743,
+      "learning_rate": 5.2222222222222226e-06,
+      "loss": 0.1328,
+      "step": 43
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 0.24794329702854156,
+      "learning_rate": 5.1111111111111115e-06,
+      "loss": 0.136,
+      "step": 44
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.20549772679805756,
+      "learning_rate": 5e-06,
+      "loss": 0.1404,
+      "step": 45
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.17471477389335632,
+      "learning_rate": 4.888888888888889e-06,
+      "loss": 0.1332,
+      "step": 46
+    },
+    {
+      "epoch": 1.5666666666666667,
+      "grad_norm": 0.171334370970726,
+      "learning_rate": 4.777777777777778e-06,
+      "loss": 0.1248,
+      "step": 47
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.20305299758911133,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.1361,
+      "step": 48
+    },
+    {
+      "epoch": 1.6333333333333333,
+      "grad_norm": 0.17506107687950134,
+      "learning_rate": 4.555555555555556e-06,
+      "loss": 0.1357,
+      "step": 49
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.1567266285419464,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.1343,
+      "step": 50
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.23731714487075806,
+      "learning_rate": 4.333333333333334e-06,
+      "loss": 0.1372,
+      "step": 51
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 0.18639369308948517,
+      "learning_rate": 4.222222222222223e-06,
+      "loss": 0.1357,
+      "step": 52
+    },
+    {
+      "epoch": 1.7666666666666666,
+      "grad_norm": 0.21129707992076874,
+      "learning_rate": 4.111111111111111e-06,
+      "loss": 0.1349,
+      "step": 53
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.17960934340953827,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.1358,
+      "step": 54
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 0.17418669164180756,
+      "learning_rate": 3.88888888888889e-06,
+      "loss": 0.1352,
+      "step": 55
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.14171800017356873,
+      "learning_rate": 3.777777777777778e-06,
+      "loss": 0.1394,
+      "step": 56
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.17009231448173523,
+      "learning_rate": 3.6666666666666666e-06,
+      "loss": 0.1397,
+      "step": 57
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 0.18514075875282288,
+      "learning_rate": 3.555555555555556e-06,
+      "loss": 0.1315,
+      "step": 58
+    },
+    {
+      "epoch": 1.9666666666666668,
+      "grad_norm": 0.2089473009109497,
+      "learning_rate": 3.444444444444445e-06,
+      "loss": 0.137,
+      "step": 59
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.14968590438365936,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.1366,
+      "step": 60
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.13573825359344482,
+      "eval_runtime": 2.6833,
+      "eval_samples_per_second": 49.566,
+      "eval_steps_per_second": 1.863,
+      "step": 60
+    },
+    {
+      "epoch": 2.033333333333333,
+      "grad_norm": 0.2098754495382309,
+      "learning_rate": 3.2222222222222227e-06,
+      "loss": 0.1367,
+      "step": 61
+    },
+    {
+      "epoch": 2.066666666666667,
+      "grad_norm": 0.16600416600704193,
+      "learning_rate": 3.1111111111111116e-06,
+      "loss": 0.1321,
+      "step": 62
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.14385317265987396,
+      "learning_rate": 3e-06,
+      "loss": 0.1322,
+      "step": 63
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.13464142382144928,
+      "learning_rate": 2.888888888888889e-06,
+      "loss": 0.1348,
+      "step": 64
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 0.22747646272182465,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 0.1361,
+      "step": 65
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.19633392989635468,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 0.136,
+      "step": 66
+    },
+    {
+      "epoch": 2.2333333333333334,
+      "grad_norm": 0.1592043936252594,
+      "learning_rate": 2.5555555555555557e-06,
+      "loss": 0.1356,
+      "step": 67
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.18236714601516724,
+      "learning_rate": 2.4444444444444447e-06,
+      "loss": 0.1363,
+      "step": 68
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.17803487181663513,
+      "learning_rate": 2.3333333333333336e-06,
+      "loss": 0.1334,
+      "step": 69
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.19840438663959503,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.136,
+      "step": 70
+    },
+    {
+      "epoch": 2.3666666666666667,
+      "grad_norm": 0.18194934725761414,
+      "learning_rate": 2.1111111111111114e-06,
+      "loss": 0.1329,
+      "step": 71
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.20873740315437317,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.1333,
+      "step": 72
+    },
+    {
+      "epoch": 2.4333333333333336,
+      "grad_norm": 0.1873055249452591,
+      "learning_rate": 1.888888888888889e-06,
+      "loss": 0.1298,
+      "step": 73
+    },
+    {
+      "epoch": 2.466666666666667,
+      "grad_norm": 0.1835811287164688,
+      "learning_rate": 1.777777777777778e-06,
+      "loss": 0.137,
+      "step": 74
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.12548275291919708,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.1283,
+      "step": 75
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 0.15173889696598053,
+      "learning_rate": 1.5555555555555558e-06,
+      "loss": 0.1308,
+      "step": 76
+    },
+    {
+      "epoch": 2.5666666666666664,
+      "grad_norm": 0.1785445660352707,
+      "learning_rate": 1.4444444444444445e-06,
+      "loss": 0.1333,
+      "step": 77
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.16538357734680176,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 0.1405,
+      "step": 78
+    },
+    {
+      "epoch": 2.6333333333333333,
+      "grad_norm": 0.12832880020141602,
+      "learning_rate": 1.2222222222222223e-06,
+      "loss": 0.1324,
+      "step": 79
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.1985386610031128,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 0.1361,
+      "step": 80
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.14083777368068695,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.1291,
+      "step": 81
+    },
+    {
+      "epoch": 2.7333333333333334,
+      "grad_norm": 0.1479172557592392,
+      "learning_rate": 8.88888888888889e-07,
+      "loss": 0.1329,
+      "step": 82
+    },
+    {
+      "epoch": 2.7666666666666666,
+      "grad_norm": 0.12942646443843842,
+      "learning_rate": 7.777777777777779e-07,
+      "loss": 0.1289,
+      "step": 83
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.1131146028637886,
+      "learning_rate": 6.666666666666667e-07,
+      "loss": 0.1296,
+      "step": 84
+    },
+    {
+      "epoch": 2.8333333333333335,
+      "grad_norm": 0.1532697081565857,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 0.1301,
+      "step": 85
+    },
+    {
+      "epoch": 2.8666666666666667,
+      "grad_norm": 0.1490510255098343,
+      "learning_rate": 4.444444444444445e-07,
+      "loss": 0.1347,
+      "step": 86
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.148887038230896,
+      "learning_rate": 3.3333333333333335e-07,
+      "loss": 0.1336,
+      "step": 87
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 0.12179289013147354,
+      "learning_rate": 2.2222222222222224e-07,
+      "loss": 0.136,
+      "step": 88
+    },
+    {
+      "epoch": 2.966666666666667,
+      "grad_norm": 0.14138825237751007,
+      "learning_rate": 1.1111111111111112e-07,
+      "loss": 0.1366,
+      "step": 89
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.128300279378891,
+      "learning_rate": 0.0,
+      "loss": 0.1366,
+      "step": 90
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.13441383838653564,
+      "eval_runtime": 2.7335,
+      "eval_samples_per_second": 48.655,
+      "eval_steps_per_second": 1.829,
+      "step": 90
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 90,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 5.829302929483366e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}