Upload folder using huggingface_hub

ft_7b_NLSY97_numeric_ckpt_bo5/config.json

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

ft_7b_NLSY97_numeric_ckpt_bo5/generation_config.json

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

ft_7b_NLSY97_numeric_ckpt_bo5/model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c0c42e75169b7054beb2d812998e2a975f7c15f1a279f6e2771bb9630e19bec
+size 4840396416

ft_7b_NLSY97_numeric_ckpt_bo5/model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:919db519ace8c570e81bc24797b64f1b02edbe9cd6d2e2ff2cc684b170a17428
+size 4857206856

ft_7b_NLSY97_numeric_ckpt_bo5/model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:870e4208762aa543b6278fed6d95fd7f9a00d65ef3ace809defc7715a82065ea
+size 4857206904

ft_7b_NLSY97_numeric_ckpt_bo5/model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6878b1f43cc2e1864d133e31e753e235f808765680c245b9075920788842fe25
+size 4857206904

ft_7b_NLSY97_numeric_ckpt_bo5/model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19e915cedea12258ac3dc656cec294aae777fc4a1ae1a1e719bcc781ec72a4db
+size 4857206904

ft_7b_NLSY97_numeric_ckpt_bo5/model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45d6f48de7ecc556d8e8759aa48745045279cba882df9c16b50da132a73eb392
+size 2684472112

ft_7b_NLSY97_numeric_ckpt_bo5/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 26953662464
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

ft_7b_NLSY97_numeric_ckpt_bo5/special_tokens_map.json

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

ft_7b_NLSY97_numeric_ckpt_bo5/tokenizer_config.json

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

ft_7b_NLSY97_numeric_ckpt_bo5/trainer_state.json

@@ -0,0 +1,668 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 17,
+  "global_step": 85,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.058823529411764705,
+      "grad_norm": 12.930320739746094,
+      "learning_rate": 9.882352941176472e-06,
+      "loss": 1.1193,
+      "step": 1
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 6.750919818878174,
+      "learning_rate": 9.764705882352942e-06,
+      "loss": 0.8447,
+      "step": 2
+    },
+    {
+      "epoch": 0.17647058823529413,
+      "grad_norm": 6.0184149742126465,
+      "learning_rate": 9.647058823529412e-06,
+      "loss": 0.5266,
+      "step": 3
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 7.928645610809326,
+      "learning_rate": 9.529411764705882e-06,
+      "loss": 0.3803,
+      "step": 4
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 5.6955156326293945,
+      "learning_rate": 9.411764705882354e-06,
+      "loss": 0.2486,
+      "step": 5
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 6.736827373504639,
+      "learning_rate": 9.294117647058824e-06,
+      "loss": 0.213,
+      "step": 6
+    },
+    {
+      "epoch": 0.4117647058823529,
+      "grad_norm": 2.5409047603607178,
+      "learning_rate": 9.176470588235294e-06,
+      "loss": 0.1947,
+      "step": 7
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 1.375417709350586,
+      "learning_rate": 9.058823529411765e-06,
+      "loss": 0.1742,
+      "step": 8
+    },
+    {
+      "epoch": 0.5294117647058824,
+      "grad_norm": 0.9182175397872925,
+      "learning_rate": 8.941176470588237e-06,
+      "loss": 0.1621,
+      "step": 9
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.7118879556655884,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 0.1573,
+      "step": 10
+    },
+    {
+      "epoch": 0.6470588235294118,
+      "grad_norm": 0.5328735709190369,
+      "learning_rate": 8.705882352941177e-06,
+      "loss": 0.1563,
+      "step": 11
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 0.5489645004272461,
+      "learning_rate": 8.588235294117647e-06,
+      "loss": 0.1471,
+      "step": 12
+    },
+    {
+      "epoch": 0.7647058823529411,
+      "grad_norm": 0.30653923749923706,
+      "learning_rate": 8.470588235294118e-06,
+      "loss": 0.1539,
+      "step": 13
+    },
+    {
+      "epoch": 0.8235294117647058,
+      "grad_norm": 0.29091715812683105,
+      "learning_rate": 8.35294117647059e-06,
+      "loss": 0.1479,
+      "step": 14
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.2531489133834839,
+      "learning_rate": 8.23529411764706e-06,
+      "loss": 0.143,
+      "step": 15
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.3365638554096222,
+      "learning_rate": 8.11764705882353e-06,
+      "loss": 0.1436,
+      "step": 16
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.20792371034622192,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.1418,
+      "step": 17
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.14182928204536438,
+      "eval_runtime": 1.6203,
+      "eval_samples_per_second": 47.521,
+      "eval_steps_per_second": 1.851,
+      "step": 17
+    },
+    {
+      "epoch": 1.0588235294117647,
+      "grad_norm": 0.2669135332107544,
+      "learning_rate": 7.882352941176471e-06,
+      "loss": 0.144,
+      "step": 18
+    },
+    {
+      "epoch": 1.1176470588235294,
+      "grad_norm": 0.2377055138349533,
+      "learning_rate": 7.764705882352941e-06,
+      "loss": 0.1406,
+      "step": 19
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.33903852105140686,
+      "learning_rate": 7.647058823529411e-06,
+      "loss": 0.1336,
+      "step": 20
+    },
+    {
+      "epoch": 1.2352941176470589,
+      "grad_norm": 0.25684112310409546,
+      "learning_rate": 7.529411764705883e-06,
+      "loss": 0.1382,
+      "step": 21
+    },
+    {
+      "epoch": 1.2941176470588236,
+      "grad_norm": 0.4274250268936157,
+      "learning_rate": 7.4117647058823535e-06,
+      "loss": 0.1333,
+      "step": 22
+    },
+    {
+      "epoch": 1.3529411764705883,
+      "grad_norm": 0.28185540437698364,
+      "learning_rate": 7.294117647058823e-06,
+      "loss": 0.1391,
+      "step": 23
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 0.3826560378074646,
+      "learning_rate": 7.176470588235295e-06,
+      "loss": 0.1307,
+      "step": 24
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 0.3587256968021393,
+      "learning_rate": 7.058823529411766e-06,
+      "loss": 0.1365,
+      "step": 25
+    },
+    {
+      "epoch": 1.5294117647058822,
+      "grad_norm": 0.35538923740386963,
+      "learning_rate": 6.941176470588236e-06,
+      "loss": 0.1308,
+      "step": 26
+    },
+    {
+      "epoch": 1.5882352941176472,
+      "grad_norm": 0.39220380783081055,
+      "learning_rate": 6.8235294117647065e-06,
+      "loss": 0.1344,
+      "step": 27
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 0.24266788363456726,
+      "learning_rate": 6.705882352941176e-06,
+      "loss": 0.1364,
+      "step": 28
+    },
+    {
+      "epoch": 1.7058823529411766,
+      "grad_norm": 0.3365913927555084,
+      "learning_rate": 6.588235294117647e-06,
+      "loss": 0.129,
+      "step": 29
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.23661571741104126,
+      "learning_rate": 6.470588235294119e-06,
+      "loss": 0.1298,
+      "step": 30
+    },
+    {
+      "epoch": 1.8235294117647058,
+      "grad_norm": 0.3883364498615265,
+      "learning_rate": 6.352941176470589e-06,
+      "loss": 0.1306,
+      "step": 31
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 0.15963129699230194,
+      "learning_rate": 6.2352941176470595e-06,
+      "loss": 0.1373,
+      "step": 32
+    },
+    {
+      "epoch": 1.9411764705882353,
+      "grad_norm": 0.3387947380542755,
+      "learning_rate": 6.11764705882353e-06,
+      "loss": 0.1336,
+      "step": 33
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.17741385102272034,
+      "learning_rate": 6e-06,
+      "loss": 0.1298,
+      "step": 34
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.1329335868358612,
+      "eval_runtime": 1.6667,
+      "eval_samples_per_second": 46.199,
+      "eval_steps_per_second": 1.8,
+      "step": 34
+    },
+    {
+      "epoch": 2.0588235294117645,
+      "grad_norm": 0.23306693136692047,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 0.1285,
+      "step": 35
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 0.20371243357658386,
+      "learning_rate": 5.764705882352941e-06,
+      "loss": 0.1306,
+      "step": 36
+    },
+    {
+      "epoch": 2.176470588235294,
+      "grad_norm": 0.2297767996788025,
+      "learning_rate": 5.6470588235294125e-06,
+      "loss": 0.1292,
+      "step": 37
+    },
+    {
+      "epoch": 2.235294117647059,
+      "grad_norm": 0.2018202394247055,
+      "learning_rate": 5.529411764705883e-06,
+      "loss": 0.132,
+      "step": 38
+    },
+    {
+      "epoch": 2.2941176470588234,
+      "grad_norm": 0.230118066072464,
+      "learning_rate": 5.411764705882353e-06,
+      "loss": 0.1319,
+      "step": 39
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 0.18205802142620087,
+      "learning_rate": 5.294117647058824e-06,
+      "loss": 0.1314,
+      "step": 40
+    },
+    {
+      "epoch": 2.411764705882353,
+      "grad_norm": 0.12206406146287918,
+      "learning_rate": 5.176470588235295e-06,
+      "loss": 0.1293,
+      "step": 41
+    },
+    {
+      "epoch": 2.4705882352941178,
+      "grad_norm": 0.21060916781425476,
+      "learning_rate": 5.058823529411765e-06,
+      "loss": 0.1312,
+      "step": 42
+    },
+    {
+      "epoch": 2.5294117647058822,
+      "grad_norm": 0.19026517868041992,
+      "learning_rate": 4.941176470588236e-06,
+      "loss": 0.1288,
+      "step": 43
+    },
+    {
+      "epoch": 2.588235294117647,
+      "grad_norm": 0.23302718997001648,
+      "learning_rate": 4.823529411764706e-06,
+      "loss": 0.1293,
+      "step": 44
+    },
+    {
+      "epoch": 2.6470588235294117,
+      "grad_norm": 0.14621809124946594,
+      "learning_rate": 4.705882352941177e-06,
+      "loss": 0.1215,
+      "step": 45
+    },
+    {
+      "epoch": 2.7058823529411766,
+      "grad_norm": 0.12860628962516785,
+      "learning_rate": 4.588235294117647e-06,
+      "loss": 0.1235,
+      "step": 46
+    },
+    {
+      "epoch": 2.764705882352941,
+      "grad_norm": 0.22921116650104523,
+      "learning_rate": 4.4705882352941184e-06,
+      "loss": 0.1282,
+      "step": 47
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 0.21150174736976624,
+      "learning_rate": 4.352941176470588e-06,
+      "loss": 0.1336,
+      "step": 48
+    },
+    {
+      "epoch": 2.8823529411764706,
+      "grad_norm": 0.14852631092071533,
+      "learning_rate": 4.235294117647059e-06,
+      "loss": 0.1288,
+      "step": 49
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.2322787493467331,
+      "learning_rate": 4.11764705882353e-06,
+      "loss": 0.1315,
+      "step": 50
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.20680484175682068,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.1271,
+      "step": 51
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.13050375878810883,
+      "eval_runtime": 1.7109,
+      "eval_samples_per_second": 45.006,
+      "eval_steps_per_second": 1.753,
+      "step": 51
+    },
+    {
+      "epoch": 3.0588235294117645,
+      "grad_norm": 0.2423618584871292,
+      "learning_rate": 3.882352941176471e-06,
+      "loss": 0.1267,
+      "step": 52
+    },
+    {
+      "epoch": 3.1176470588235294,
+      "grad_norm": 0.15684513747692108,
+      "learning_rate": 3.7647058823529414e-06,
+      "loss": 0.1271,
+      "step": 53
+    },
+    {
+      "epoch": 3.176470588235294,
+      "grad_norm": 0.17888614535331726,
+      "learning_rate": 3.6470588235294117e-06,
+      "loss": 0.1292,
+      "step": 54
+    },
+    {
+      "epoch": 3.235294117647059,
+      "grad_norm": 0.1872224360704422,
+      "learning_rate": 3.529411764705883e-06,
+      "loss": 0.1265,
+      "step": 55
+    },
+    {
+      "epoch": 3.2941176470588234,
+      "grad_norm": 0.18106265366077423,
+      "learning_rate": 3.4117647058823532e-06,
+      "loss": 0.125,
+      "step": 56
+    },
+    {
+      "epoch": 3.3529411764705883,
+      "grad_norm": 0.16410322487354279,
+      "learning_rate": 3.2941176470588236e-06,
+      "loss": 0.1247,
+      "step": 57
+    },
+    {
+      "epoch": 3.411764705882353,
+      "grad_norm": 0.14523057639598846,
+      "learning_rate": 3.1764705882352943e-06,
+      "loss": 0.1293,
+      "step": 58
+    },
+    {
+      "epoch": 3.4705882352941178,
+      "grad_norm": 0.14566871523857117,
+      "learning_rate": 3.058823529411765e-06,
+      "loss": 0.1229,
+      "step": 59
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 0.17588646709918976,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 0.1293,
+      "step": 60
+    },
+    {
+      "epoch": 3.588235294117647,
+      "grad_norm": 0.16981141269207,
+      "learning_rate": 2.8235294117647062e-06,
+      "loss": 0.127,
+      "step": 61
+    },
+    {
+      "epoch": 3.6470588235294117,
+      "grad_norm": 0.13811074197292328,
+      "learning_rate": 2.7058823529411766e-06,
+      "loss": 0.1274,
+      "step": 62
+    },
+    {
+      "epoch": 3.7058823529411766,
+      "grad_norm": 0.11759057641029358,
+      "learning_rate": 2.5882352941176473e-06,
+      "loss": 0.1246,
+      "step": 63
+    },
+    {
+      "epoch": 3.764705882352941,
+      "grad_norm": 0.1862180382013321,
+      "learning_rate": 2.470588235294118e-06,
+      "loss": 0.136,
+      "step": 64
+    },
+    {
+      "epoch": 3.8235294117647056,
+      "grad_norm": 0.14767520129680634,
+      "learning_rate": 2.3529411764705885e-06,
+      "loss": 0.126,
+      "step": 65
+    },
+    {
+      "epoch": 3.8823529411764706,
+      "grad_norm": 0.1449473798274994,
+      "learning_rate": 2.2352941176470592e-06,
+      "loss": 0.1233,
+      "step": 66
+    },
+    {
+      "epoch": 3.9411764705882355,
+      "grad_norm": 0.1184178814291954,
+      "learning_rate": 2.1176470588235296e-06,
+      "loss": 0.1263,
+      "step": 67
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.13197602331638336,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.1254,
+      "step": 68
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.12875893712043762,
+      "eval_runtime": 1.7604,
+      "eval_samples_per_second": 43.741,
+      "eval_steps_per_second": 1.704,
+      "step": 68
+    },
+    {
+      "epoch": 4.0588235294117645,
+      "grad_norm": 0.13755379617214203,
+      "learning_rate": 1.8823529411764707e-06,
+      "loss": 0.1238,
+      "step": 69
+    },
+    {
+      "epoch": 4.117647058823529,
+      "grad_norm": 0.09173008054494858,
+      "learning_rate": 1.7647058823529414e-06,
+      "loss": 0.1267,
+      "step": 70
+    },
+    {
+      "epoch": 4.176470588235294,
+      "grad_norm": 0.16052384674549103,
+      "learning_rate": 1.6470588235294118e-06,
+      "loss": 0.1238,
+      "step": 71
+    },
+    {
+      "epoch": 4.235294117647059,
+      "grad_norm": 0.11233089119195938,
+      "learning_rate": 1.5294117647058826e-06,
+      "loss": 0.1277,
+      "step": 72
+    },
+    {
+      "epoch": 4.294117647058823,
+      "grad_norm": 0.10879813879728317,
+      "learning_rate": 1.4117647058823531e-06,
+      "loss": 0.1239,
+      "step": 73
+    },
+    {
+      "epoch": 4.352941176470588,
+      "grad_norm": 0.14366036653518677,
+      "learning_rate": 1.2941176470588237e-06,
+      "loss": 0.1279,
+      "step": 74
+    },
+    {
+      "epoch": 4.411764705882353,
+      "grad_norm": 0.15720945596694946,
+      "learning_rate": 1.1764705882352942e-06,
+      "loss": 0.1257,
+      "step": 75
+    },
+    {
+      "epoch": 4.470588235294118,
+      "grad_norm": 0.111957848072052,
+      "learning_rate": 1.0588235294117648e-06,
+      "loss": 0.1272,
+      "step": 76
+    },
+    {
+      "epoch": 4.529411764705882,
+      "grad_norm": 0.10795588046312332,
+      "learning_rate": 9.411764705882353e-07,
+      "loss": 0.1217,
+      "step": 77
+    },
+    {
+      "epoch": 4.588235294117647,
+      "grad_norm": 0.13502325117588043,
+      "learning_rate": 8.235294117647059e-07,
+      "loss": 0.1264,
+      "step": 78
+    },
+    {
+      "epoch": 4.647058823529412,
+      "grad_norm": 0.19920289516448975,
+      "learning_rate": 7.058823529411766e-07,
+      "loss": 0.1264,
+      "step": 79
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 0.11849205940961838,
+      "learning_rate": 5.882352941176471e-07,
+      "loss": 0.1333,
+      "step": 80
+    },
+    {
+      "epoch": 4.764705882352941,
+      "grad_norm": 0.11072594672441483,
+      "learning_rate": 4.7058823529411767e-07,
+      "loss": 0.1241,
+      "step": 81
+    },
+    {
+      "epoch": 4.823529411764706,
+      "grad_norm": 0.13145644962787628,
+      "learning_rate": 3.529411764705883e-07,
+      "loss": 0.1199,
+      "step": 82
+    },
+    {
+      "epoch": 4.882352941176471,
+      "grad_norm": 0.12302340567111969,
+      "learning_rate": 2.3529411764705883e-07,
+      "loss": 0.1245,
+      "step": 83
+    },
+    {
+      "epoch": 4.9411764705882355,
+      "grad_norm": 0.147792249917984,
+      "learning_rate": 1.1764705882352942e-07,
+      "loss": 0.1237,
+      "step": 84
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.11199651658535004,
+      "learning_rate": 0.0,
+      "loss": 0.1218,
+      "step": 85
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.12799321115016937,
+      "eval_runtime": 1.7984,
+      "eval_samples_per_second": 42.815,
+      "eval_steps_per_second": 1.668,
+      "step": 85
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 85,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 17,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.507088503537664e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}