Initial commit

.gitattributes

@@ -0,0 +1,3 @@
+pytorch_model-00001-of-00003.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00002-of-00003.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00003-of-00003.bin filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "yahma/llama-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.1"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b74b8772eea86be2a81e62a63f715dfa6efe28fc16915e6a7880147ad7a38c71
+size 9878009874

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:606a80c184ee9a0d28214060cee216be46fd7c13103505a2a871fefdd7c1d3c6
+size 9894805046

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58297e1803a1af25bfbc50e52a4506e4cb048199a1f75b34c8166724521d8b5c
+size 7181009913

pytorch_model.bin.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 26953703424
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
+    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_fast": false
+}

trainer_state.json

@@ -0,0 +1,817 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.962131837307153,
+  "global_step": 132,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 5e-06,
+      "loss": 1.5608,
+      "step": 1
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1e-05,
+      "loss": 1.537,
+      "step": 2
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.4795,
+      "step": 3
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2e-05,
+      "loss": 1.369,
+      "step": 4
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9996988186962044e-05,
+      "loss": 1.3342,
+      "step": 5
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9987954562051724e-05,
+      "loss": 1.3373,
+      "step": 6
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9972904566786903e-05,
+      "loss": 1.2752,
+      "step": 7
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.995184726672197e-05,
+      "loss": 1.3176,
+      "step": 8
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9924795345987103e-05,
+      "loss": 1.3508,
+      "step": 9
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.989176509964781e-05,
+      "loss": 1.3623,
+      "step": 10
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9852776423889414e-05,
+      "loss": 1.3363,
+      "step": 11
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9807852804032306e-05,
+      "loss": 1.2854,
+      "step": 12
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9757021300385288e-05,
+      "loss": 1.3665,
+      "step": 13
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9700312531945444e-05,
+      "loss": 1.3254,
+      "step": 14
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.96377606579544e-05,
+      "loss": 1.3074,
+      "step": 15
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.956940335732209e-05,
+      "loss": 1.2471,
+      "step": 16
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.949528180593037e-05,
+      "loss": 1.295,
+      "step": 17
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.941544065183021e-05,
+      "loss": 1.3434,
+      "step": 18
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.932992798834739e-05,
+      "loss": 1.319,
+      "step": 19
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9238795325112867e-05,
+      "loss": 1.3529,
+      "step": 20
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.914209755703531e-05,
+      "loss": 1.3155,
+      "step": 21
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9039892931234434e-05,
+      "loss": 1.3072,
+      "step": 22
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.8932243011955154e-05,
+      "loss": 1.2897,
+      "step": 23
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.881921264348355e-05,
+      "loss": 1.382,
+      "step": 24
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.8700869911087115e-05,
+      "loss": 1.3016,
+      "step": 25
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.8577286100002723e-05,
+      "loss": 1.2886,
+      "step": 26
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.8448535652497073e-05,
+      "loss": 1.3313,
+      "step": 27
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8314696123025456e-05,
+      "loss": 1.301,
+      "step": 28
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.817584813151584e-05,
+      "loss": 1.3474,
+      "step": 29
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.803207531480645e-05,
+      "loss": 1.3523,
+      "step": 30
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.7883464276266064e-05,
+      "loss": 1.3423,
+      "step": 31
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.773010453362737e-05,
+      "loss": 1.2947,
+      "step": 32
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.7572088465064847e-05,
+      "loss": 1.3074,
+      "step": 33
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.7409511253549592e-05,
+      "loss": 1.3555,
+      "step": 34
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.7242470829514674e-05,
+      "loss": 1.2528,
+      "step": 35
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 1.3164,
+      "step": 36
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.689540544737067e-05,
+      "loss": 1.3135,
+      "step": 37
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6715589548470187e-05,
+      "loss": 1.3569,
+      "step": 38
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6531728429537766e-05,
+      "loss": 1.2685,
+      "step": 39
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.6343932841636455e-05,
+      "loss": 1.3216,
+      "step": 40
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.615231590580627e-05,
+      "loss": 1.3005,
+      "step": 41
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.5956993044924334e-05,
+      "loss": 1.2982,
+      "step": 42
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.5758081914178457e-05,
+      "loss": 1.272,
+      "step": 43
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5555702330196024e-05,
+      "loss": 1.3246,
+      "step": 44
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.5349976198870974e-05,
+      "loss": 1.1729,
+      "step": 45
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.5141027441932217e-05,
+      "loss": 0.9817,
+      "step": 46
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.4928981922297842e-05,
+      "loss": 0.9715,
+      "step": 47
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.4713967368259981e-05,
+      "loss": 0.9656,
+      "step": 48
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.4496113296546068e-05,
+      "loss": 0.9229,
+      "step": 49
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.4275550934302822e-05,
+      "loss": 0.9596,
+      "step": 50
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.4052413140049898e-05,
+      "loss": 0.8889,
+      "step": 51
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.3826834323650899e-05,
+      "loss": 0.8685,
+      "step": 52
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.3598950365349884e-05,
+      "loss": 0.939,
+      "step": 53
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.3368898533922202e-05,
+      "loss": 0.9308,
+      "step": 54
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.3136817403988918e-05,
+      "loss": 0.8947,
+      "step": 55
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.2902846772544625e-05,
+      "loss": 0.8729,
+      "step": 56
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.2667127574748985e-05,
+      "loss": 0.9327,
+      "step": 57
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.242980179903264e-05,
+      "loss": 0.8962,
+      "step": 58
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.2191012401568698e-05,
+      "loss": 0.8523,
+      "step": 59
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.1950903220161286e-05,
+      "loss": 0.871,
+      "step": 60
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.1709618887603013e-05,
+      "loss": 0.8349,
+      "step": 61
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.1467304744553618e-05,
+      "loss": 0.8938,
+      "step": 62
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1224106751992164e-05,
+      "loss": 0.8923,
+      "step": 63
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.098017140329561e-05,
+      "loss": 0.8612,
+      "step": 64
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.0735645635996676e-05,
+      "loss": 0.8725,
+      "step": 65
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0490676743274181e-05,
+      "loss": 0.8748,
+      "step": 66
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0245412285229124e-05,
+      "loss": 0.9522,
+      "step": 67
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1e-05,
+      "loss": 0.8638,
+      "step": 68
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.75458771477088e-06,
+      "loss": 0.9168,
+      "step": 69
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.50932325672582e-06,
+      "loss": 0.8194,
+      "step": 70
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 9.264354364003327e-06,
+      "loss": 0.8645,
+      "step": 71
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.019828596704394e-06,
+      "loss": 0.8697,
+      "step": 72
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 8.77589324800784e-06,
+      "loss": 0.8475,
+      "step": 73
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.532695255446384e-06,
+      "loss": 0.8619,
+      "step": 74
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.290381112396989e-06,
+      "loss": 0.8899,
+      "step": 75
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.04909677983872e-06,
+      "loss": 0.8624,
+      "step": 76
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 7.808987598431303e-06,
+      "loss": 0.8264,
+      "step": 77
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.570198200967363e-06,
+      "loss": 0.8601,
+      "step": 78
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.332872425251017e-06,
+      "loss": 0.8805,
+      "step": 79
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.097153227455379e-06,
+      "loss": 0.8609,
+      "step": 80
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 6.8631825960110866e-06,
+      "loss": 0.8157,
+      "step": 81
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 6.631101466077801e-06,
+      "loss": 0.8573,
+      "step": 82
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.401049634650119e-06,
+      "loss": 0.8475,
+      "step": 83
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 6.173165676349103e-06,
+      "loss": 0.9107,
+      "step": 84
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 5.947586859950103e-06,
+      "loss": 0.8895,
+      "step": 85
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 5.724449065697182e-06,
+      "loss": 0.9007,
+      "step": 86
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 5.503886703453933e-06,
+      "loss": 0.8571,
+      "step": 87
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5.286032631740023e-06,
+      "loss": 0.8509,
+      "step": 88
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.071018077702161e-06,
+      "loss": 0.8653,
+      "step": 89
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 4.858972558067784e-06,
+      "loss": 0.712,
+      "step": 90
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 4.65002380112903e-06,
+      "loss": 0.67,
+      "step": 91
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 4.444297669803981e-06,
+      "loss": 0.6964,
+      "step": 92
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.241918085821547e-06,
+      "loss": 0.6407,
+      "step": 93
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 4.043006955075667e-06,
+      "loss": 0.6147,
+      "step": 94
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 3.847684094193733e-06,
+      "loss": 0.6482,
+      "step": 95
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 3.6560671583635467e-06,
+      "loss": 0.642,
+      "step": 96
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 3.468271570462235e-06,
+      "loss": 0.6269,
+      "step": 97
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.284410451529816e-06,
+      "loss": 0.595,
+      "step": 98
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.1045945526293307e-06,
+      "loss": 0.6096,
+      "step": 99
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.63,
+      "step": 100
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.7575291704853325e-06,
+      "loss": 0.628,
+      "step": 101
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.5904887464504115e-06,
+      "loss": 0.6283,
+      "step": 102
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.4279115349351546e-06,
+      "loss": 0.6003,
+      "step": 103
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.26989546637263e-06,
+      "loss": 0.6256,
+      "step": 104
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.116535723733938e-06,
+      "loss": 0.5855,
+      "step": 105
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 1.967924685193552e-06,
+      "loss": 0.6104,
+      "step": 106
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.8241518684841642e-06,
+      "loss": 0.611,
+      "step": 107
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.6853038769745466e-06,
+      "loss": 0.6471,
+      "step": 108
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.551464347502929e-06,
+      "loss": 0.5739,
+      "step": 109
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.4227138999972801e-06,
+      "loss": 0.5972,
+      "step": 110
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.2991300889128867e-06,
+      "loss": 0.635,
+      "step": 111
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.1807873565164507e-06,
+      "loss": 0.6071,
+      "step": 112
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.0677569880448479e-06,
+      "loss": 0.5941,
+      "step": 113
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 9.601070687655667e-07,
+      "loss": 0.6395,
+      "step": 114
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 8.579024429646932e-07,
+      "loss": 0.625,
+      "step": 115
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 7.612046748871327e-07,
+      "loss": 0.6235,
+      "step": 116
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 6.700720116526116e-07,
+      "loss": 0.6185,
+      "step": 117
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 5.845593481697931e-07,
+      "loss": 0.5909,
+      "step": 118
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 5.047181940696333e-07,
+      "loss": 0.6195,
+      "step": 119
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 4.305966426779118e-07,
+      "loss": 0.5715,
+      "step": 120
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 3.6223934204560165e-07,
+      "loss": 0.6129,
+      "step": 121
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 2.996874680545603e-07,
+      "loss": 0.601,
+      "step": 122
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 2.4297869961471544e-07,
+      "loss": 0.5971,
+      "step": 123
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 1.921471959676957e-07,
+      "loss": 0.6276,
+      "step": 124
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.472235761105878e-07,
+      "loss": 0.6267,
+      "step": 125
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.0823490035218986e-07,
+      "loss": 0.5968,
+      "step": 126
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 7.520465401290033e-08,
+      "loss": 0.64,
+      "step": 127
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 4.815273327803183e-08,
+      "loss": 0.6304,
+      "step": 128
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 2.7095433213097933e-08,
+      "loss": 0.5567,
+      "step": 129
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 1.2045437948275952e-08,
+      "loss": 0.6299,
+      "step": 130
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 3.0118130379575005e-09,
+      "loss": 0.6133,
+      "step": 131
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 0.0,
+      "loss": 0.6049,
+      "step": 132
+    },
+    {
+      "epoch": 2.96,
+      "step": 132,
+      "total_flos": 8.052252031844352e+16,
+      "train_loss": 0.9501514579310562,
+      "train_runtime": 19803.7183,
+      "train_samples_per_second": 0.864,
+      "train_steps_per_second": 0.007
+    }
+  ],
+  "max_steps": 132,
+  "num_train_epochs": 3,
+  "total_flos": 8.052252031844352e+16,
+  "trial_name": null,
+  "trial_params": null
+}