Upload folder using huggingface_hub

ft_13b_NLSY79_with_birth_year_ckpt_3/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "togethercomputer/llama-2-13b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

ft_13b_NLSY79_with_birth_year_ckpt_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": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.45.1"
+}

ft_13b_NLSY79_with_birth_year_ckpt_3/model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80fc9efbb305ed7bee48f382d39f8381939a6bee6298590ba86e6e1889015da9
+size 4881247856

ft_13b_NLSY79_with_birth_year_ckpt_3/model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7a9140b4aa42a813911cfc134e42534a31cb08a4ff849267f78d6a4a80cd0b8
+size 4970418112

ft_13b_NLSY79_with_birth_year_ckpt_3/model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af7fd08dcfaf2579ba153e51c2c675611b65cd9fe644d8ff3b1c62f8341ca8b6
+size 4970418120

ft_13b_NLSY79_with_birth_year_ckpt_3/model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50d227d8549c40b18014199eb42baa478ffdfe923e94507f1dcd1daf8975fa87
+size 4970418144

ft_13b_NLSY79_with_birth_year_ckpt_3/model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:999e4d4373bb8718fcb6d4890d69a6d349c46c4e2e1a607fca3a63a566289a99
+size 4970418144

ft_13b_NLSY79_with_birth_year_ckpt_3/model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:145b54b90b462ddae21b4f88771b8eabbeccaa1cec899d676cdcf12cd82015fe
+size 4792119040

ft_13b_NLSY79_with_birth_year_ckpt_3/model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4a92d2f2bef6093c58e2ad383d79602439b404b3ff44649e08a8e6893924384
+size 4792160232

ft_13b_NLSY79_with_birth_year_ckpt_3/model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1903719bcdf36504e73e7aabbe86ced67735cbe4bcc9a814dbc9e2af4148847a
+size 4792160224

ft_13b_NLSY79_with_birth_year_ckpt_3/model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37928acbe045a6687071ee7771ef6d2404488ec9d910db9bf847d4b81f58b0d2
+size 4970418144

ft_13b_NLSY79_with_birth_year_ckpt_3/model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e10a2f2df781dc8b7f39b440beec3c6b88eb7ff7ccfaab11bd4ecc6eb4506a28
+size 4970418144

ft_13b_NLSY79_with_birth_year_ckpt_3/model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efffa86d04cdfb248e62d7255e2ee73d1ded60bfe06d7a17d0fe02403a623a1c
+size 2983303184

ft_13b_NLSY79_with_birth_year_ckpt_3/model.safetensors.index.json

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

ft_13b_NLSY79_with_birth_year_ckpt_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_13b_NLSY79_with_birth_year_ckpt_3/tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' or message['role'] == 'tool' %}{{ bos_token + '[INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'system' %}{{ '<<SYS>>\\n' + content + '\\n<</SYS>>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

ft_13b_NLSY79_with_birth_year_ckpt_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": 6.756654739379883,
+      "learning_rate": 9.88888888888889e-06,
+      "loss": 0.9896,
+      "step": 1
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 4.388773441314697,
+      "learning_rate": 9.777777777777779e-06,
+      "loss": 0.6516,
+      "step": 2
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 11.626699447631836,
+      "learning_rate": 9.666666666666667e-06,
+      "loss": 0.401,
+      "step": 3
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 3.3663454055786133,
+      "learning_rate": 9.555555555555556e-06,
+      "loss": 0.2648,
+      "step": 4
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 5.141721248626709,
+      "learning_rate": 9.444444444444445e-06,
+      "loss": 0.2652,
+      "step": 5
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.9627482891082764,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 0.181,
+      "step": 6
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 0.7184298634529114,
+      "learning_rate": 9.222222222222224e-06,
+      "loss": 0.1733,
+      "step": 7
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.6345965266227722,
+      "learning_rate": 9.111111111111112e-06,
+      "loss": 0.171,
+      "step": 8
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.4310895502567291,
+      "learning_rate": 9e-06,
+      "loss": 0.1578,
+      "step": 9
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.42963308095932007,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.1588,
+      "step": 10
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 0.3190704882144928,
+      "learning_rate": 8.777777777777778e-06,
+      "loss": 0.1528,
+      "step": 11
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.34697574377059937,
+      "learning_rate": 8.666666666666668e-06,
+      "loss": 0.157,
+      "step": 12
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 0.2627966105937958,
+      "learning_rate": 8.555555555555556e-06,
+      "loss": 0.1548,
+      "step": 13
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.23730801045894623,
+      "learning_rate": 8.444444444444446e-06,
+      "loss": 0.1528,
+      "step": 14
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.27259665727615356,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.1406,
+      "step": 15
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.19127672910690308,
+      "learning_rate": 8.222222222222222e-06,
+      "loss": 0.1443,
+      "step": 16
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 0.18087811768054962,
+      "learning_rate": 8.111111111111112e-06,
+      "loss": 0.1439,
+      "step": 17
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.23132827877998352,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.1463,
+      "step": 18
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 0.17551013827323914,
+      "learning_rate": 7.88888888888889e-06,
+      "loss": 0.1373,
+      "step": 19
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.16079062223434448,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 0.1442,
+      "step": 20
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.16452927887439728,
+      "learning_rate": 7.666666666666667e-06,
+      "loss": 0.1462,
+      "step": 21
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.144525945186615,
+      "learning_rate": 7.555555555555556e-06,
+      "loss": 0.1444,
+      "step": 22
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 0.14696849882602692,
+      "learning_rate": 7.444444444444445e-06,
+      "loss": 0.1387,
+      "step": 23
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.16059017181396484,
+      "learning_rate": 7.333333333333333e-06,
+      "loss": 0.1315,
+      "step": 24
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.16093049943447113,
+      "learning_rate": 7.222222222222223e-06,
+      "loss": 0.138,
+      "step": 25
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.1766657531261444,
+      "learning_rate": 7.111111111111112e-06,
+      "loss": 0.1367,
+      "step": 26
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.22861993312835693,
+      "learning_rate": 7e-06,
+      "loss": 0.1413,
+      "step": 27
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.1955043077468872,
+      "learning_rate": 6.88888888888889e-06,
+      "loss": 0.1472,
+      "step": 28
+    },
+    {
+      "epoch": 0.9666666666666667,
+      "grad_norm": 0.20372217893600464,
+      "learning_rate": 6.777777777777779e-06,
+      "loss": 0.143,
+      "step": 29
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.2251114398241043,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.1437,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.1389642059803009,
+      "eval_runtime": 5.0801,
+      "eval_samples_per_second": 26.18,
+      "eval_steps_per_second": 0.984,
+      "step": 30
+    },
+    {
+      "epoch": 1.0333333333333334,
+      "grad_norm": 0.24110844731330872,
+      "learning_rate": 6.555555555555556e-06,
+      "loss": 0.1467,
+      "step": 31
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.13794952630996704,
+      "learning_rate": 6.444444444444445e-06,
+      "loss": 0.1328,
+      "step": 32
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.1344776451587677,
+      "learning_rate": 6.333333333333333e-06,
+      "loss": 0.1416,
+      "step": 33
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.15418794751167297,
+      "learning_rate": 6.222222222222223e-06,
+      "loss": 0.1347,
+      "step": 34
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.12393444776535034,
+      "learning_rate": 6.111111111111112e-06,
+      "loss": 0.1387,
+      "step": 35
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.12951317429542542,
+      "learning_rate": 6e-06,
+      "loss": 0.1279,
+      "step": 36
+    },
+    {
+      "epoch": 1.2333333333333334,
+      "grad_norm": 0.1566055864095688,
+      "learning_rate": 5.88888888888889e-06,
+      "loss": 0.1403,
+      "step": 37
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.11854217946529388,
+      "learning_rate": 5.777777777777778e-06,
+      "loss": 0.134,
+      "step": 38
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.1250990331172943,
+      "learning_rate": 5.666666666666667e-06,
+      "loss": 0.1309,
+      "step": 39
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.12426821887493134,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 0.1348,
+      "step": 40
+    },
+    {
+      "epoch": 1.3666666666666667,
+      "grad_norm": 0.14265167713165283,
+      "learning_rate": 5.444444444444445e-06,
+      "loss": 0.1411,
+      "step": 41
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.14097608625888824,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 0.1366,
+      "step": 42
+    },
+    {
+      "epoch": 1.4333333333333333,
+      "grad_norm": 0.13661041855812073,
+      "learning_rate": 5.2222222222222226e-06,
+      "loss": 0.1382,
+      "step": 43
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 0.15367251634597778,
+      "learning_rate": 5.1111111111111115e-06,
+      "loss": 0.1345,
+      "step": 44
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.13000041246414185,
+      "learning_rate": 5e-06,
+      "loss": 0.1361,
+      "step": 45
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.1131439059972763,
+      "learning_rate": 4.888888888888889e-06,
+      "loss": 0.1339,
+      "step": 46
+    },
+    {
+      "epoch": 1.5666666666666667,
+      "grad_norm": 0.15624798834323883,
+      "learning_rate": 4.777777777777778e-06,
+      "loss": 0.135,
+      "step": 47
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.13269546627998352,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.1334,
+      "step": 48
+    },
+    {
+      "epoch": 1.6333333333333333,
+      "grad_norm": 0.11152497678995132,
+      "learning_rate": 4.555555555555556e-06,
+      "loss": 0.1425,
+      "step": 49
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.13962796330451965,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.1342,
+      "step": 50
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.12835395336151123,
+      "learning_rate": 4.333333333333334e-06,
+      "loss": 0.1352,
+      "step": 51
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 0.12098712474107742,
+      "learning_rate": 4.222222222222223e-06,
+      "loss": 0.1341,
+      "step": 52
+    },
+    {
+      "epoch": 1.7666666666666666,
+      "grad_norm": 0.11860781908035278,
+      "learning_rate": 4.111111111111111e-06,
+      "loss": 0.1347,
+      "step": 53
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.11772364377975464,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.1342,
+      "step": 54
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 0.12149743735790253,
+      "learning_rate": 3.88888888888889e-06,
+      "loss": 0.1375,
+      "step": 55
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.13157767057418823,
+      "learning_rate": 3.777777777777778e-06,
+      "loss": 0.1354,
+      "step": 56
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.11540118604898453,
+      "learning_rate": 3.6666666666666666e-06,
+      "loss": 0.1341,
+      "step": 57
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 0.14963074028491974,
+      "learning_rate": 3.555555555555556e-06,
+      "loss": 0.1359,
+      "step": 58
+    },
+    {
+      "epoch": 1.9666666666666668,
+      "grad_norm": 0.13901227712631226,
+      "learning_rate": 3.444444444444445e-06,
+      "loss": 0.1336,
+      "step": 59
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.11229171603918076,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.1369,
+      "step": 60
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.13511531054973602,
+      "eval_runtime": 5.1098,
+      "eval_samples_per_second": 26.028,
+      "eval_steps_per_second": 0.979,
+      "step": 60
+    },
+    {
+      "epoch": 2.033333333333333,
+      "grad_norm": 0.12950368225574493,
+      "learning_rate": 3.2222222222222227e-06,
+      "loss": 0.1275,
+      "step": 61
+    },
+    {
+      "epoch": 2.066666666666667,
+      "grad_norm": 0.10755325108766556,
+      "learning_rate": 3.1111111111111116e-06,
+      "loss": 0.1384,
+      "step": 62
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.12992867827415466,
+      "learning_rate": 3e-06,
+      "loss": 0.1364,
+      "step": 63
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.1376504898071289,
+      "learning_rate": 2.888888888888889e-06,
+      "loss": 0.1406,
+      "step": 64
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 0.11081744730472565,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 0.1333,
+      "step": 65
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.09679851680994034,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 0.136,
+      "step": 66
+    },
+    {
+      "epoch": 2.2333333333333334,
+      "grad_norm": 0.13199330866336823,
+      "learning_rate": 2.5555555555555557e-06,
+      "loss": 0.1294,
+      "step": 67
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.12924429774284363,
+      "learning_rate": 2.4444444444444447e-06,
+      "loss": 0.1349,
+      "step": 68
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.1062309667468071,
+      "learning_rate": 2.3333333333333336e-06,
+      "loss": 0.133,
+      "step": 69
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.10067743808031082,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 0.1382,
+      "step": 70
+    },
+    {
+      "epoch": 2.3666666666666667,
+      "grad_norm": 0.14575141668319702,
+      "learning_rate": 2.1111111111111114e-06,
+      "loss": 0.1338,
+      "step": 71
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.10778827965259552,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.1363,
+      "step": 72
+    },
+    {
+      "epoch": 2.4333333333333336,
+      "grad_norm": 0.10342462360858917,
+      "learning_rate": 1.888888888888889e-06,
+      "loss": 0.1282,
+      "step": 73
+    },
+    {
+      "epoch": 2.466666666666667,
+      "grad_norm": 0.0964592695236206,
+      "learning_rate": 1.777777777777778e-06,
+      "loss": 0.1334,
+      "step": 74
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.12873083353042603,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.1373,
+      "step": 75
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 0.14387091994285583,
+      "learning_rate": 1.5555555555555558e-06,
+      "loss": 0.1354,
+      "step": 76
+    },
+    {
+      "epoch": 2.5666666666666664,
+      "grad_norm": 0.12266004085540771,
+      "learning_rate": 1.4444444444444445e-06,
+      "loss": 0.1309,
+      "step": 77
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.08805371820926666,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 0.1341,
+      "step": 78
+    },
+    {
+      "epoch": 2.6333333333333333,
+      "grad_norm": 0.11398159712553024,
+      "learning_rate": 1.2222222222222223e-06,
+      "loss": 0.1336,
+      "step": 79
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.10753536969423294,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 0.1304,
+      "step": 80
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.12526370584964752,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.1359,
+      "step": 81
+    },
+    {
+      "epoch": 2.7333333333333334,
+      "grad_norm": 0.1131182312965393,
+      "learning_rate": 8.88888888888889e-07,
+      "loss": 0.1306,
+      "step": 82
+    },
+    {
+      "epoch": 2.7666666666666666,
+      "grad_norm": 0.10941901803016663,
+      "learning_rate": 7.777777777777779e-07,
+      "loss": 0.1271,
+      "step": 83
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.09163400530815125,
+      "learning_rate": 6.666666666666667e-07,
+      "loss": 0.1346,
+      "step": 84
+    },
+    {
+      "epoch": 2.8333333333333335,
+      "grad_norm": 0.09697934240102768,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 0.1265,
+      "step": 85
+    },
+    {
+      "epoch": 2.8666666666666667,
+      "grad_norm": 0.098645880818367,
+      "learning_rate": 4.444444444444445e-07,
+      "loss": 0.1284,
+      "step": 86
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.11068296432495117,
+      "learning_rate": 3.3333333333333335e-07,
+      "loss": 0.1318,
+      "step": 87
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 0.10501579940319061,
+      "learning_rate": 2.2222222222222224e-07,
+      "loss": 0.1256,
+      "step": 88
+    },
+    {
+      "epoch": 2.966666666666667,
+      "grad_norm": 0.11091522872447968,
+      "learning_rate": 1.1111111111111112e-07,
+      "loss": 0.1328,
+      "step": 89
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.10818880051374435,
+      "learning_rate": 0.0,
+      "loss": 0.1254,
+      "step": 90
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.13397298753261566,
+      "eval_runtime": 5.2044,
+      "eval_samples_per_second": 25.555,
+      "eval_steps_per_second": 0.961,
+      "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": 1.133858697332654e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}