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 sha256:34eb6cf81eb7b232f44357632ef37884a61c4190968eb582484a11cdd06fafb5
+size 9878009874

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82a963405f08e84056b69f0c97a30604133d037ab9ee25928bed00cd472a34b5
+size 9894805046

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70258ce0fdd295870f292284eb07d23f525b74100ba56f61457b4e925c5af667
+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": 1024,
+  "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 +1,997 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.970773638968481,
+  "global_step": 162,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.1016,
+      "step": 1
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.1368,
+      "step": 2
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.2e-05,
+      "loss": 0.9796,
+      "step": 3
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.8796,
+      "step": 4
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2e-05,
+      "loss": 0.9098,
+      "step": 5
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9997998037428528e-05,
+      "loss": 0.891,
+      "step": 6
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.999199295128493e-05,
+      "loss": 0.8434,
+      "step": 7
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.998198714596076e-05,
+      "loss": 0.8646,
+      "step": 8
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.996798462770555e-05,
+      "loss": 0.8441,
+      "step": 9
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.994999100302281e-05,
+      "loss": 0.8292,
+      "step": 10
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.992801347642515e-05,
+      "loss": 0.8532,
+      "step": 11
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9902060847549716e-05,
+      "loss": 0.9236,
+      "step": 12
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.987214350763483e-05,
+      "loss": 0.8709,
+      "step": 13
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9838273435359447e-05,
+      "loss": 0.8258,
+      "step": 14
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9800464192046956e-05,
+      "loss": 0.8295,
+      "step": 15
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9758730916235356e-05,
+      "loss": 0.8563,
+      "step": 16
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9713090317615877e-05,
+      "loss": 0.8107,
+      "step": 17
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.966356067034256e-05,
+      "loss": 0.7892,
+      "step": 18
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.96101618057154e-05,
+      "loss": 0.8178,
+      "step": 19
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9552915104240067e-05,
+      "loss": 0.8068,
+      "step": 20
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9491843487067305e-05,
+      "loss": 0.8412,
+      "step": 21
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.9426971406815464e-05,
+      "loss": 0.8227,
+      "step": 22
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9358324837779864e-05,
+      "loss": 0.8498,
+      "step": 23
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9285931265532875e-05,
+      "loss": 0.8139,
+      "step": 24
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.920981967591891e-05,
+      "loss": 0.8362,
+      "step": 25
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9130020543448705e-05,
+      "loss": 0.8154,
+      "step": 26
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.9046565819097546e-05,
+      "loss": 0.7701,
+      "step": 27
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.895948891751234e-05,
+      "loss": 0.8314,
+      "step": 28
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.8868824703632658e-05,
+      "loss": 0.8286,
+      "step": 29
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.8774609478731048e-05,
+      "loss": 0.84,
+      "step": 30
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.8676880965878293e-05,
+      "loss": 0.8277,
+      "step": 31
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.857567829483937e-05,
+      "loss": 0.8626,
+      "step": 32
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.84710419864062e-05,
+      "loss": 0.7764,
+      "step": 33
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8363013936173393e-05,
+      "loss": 0.7994,
+      "step": 34
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8251637397763597e-05,
+      "loss": 0.7772,
+      "step": 35
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.8136956965509064e-05,
+      "loss": 0.8424,
+      "step": 36
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8019018556596402e-05,
+      "loss": 0.8108,
+      "step": 37
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.7897869392681685e-05,
+      "loss": 0.8084,
+      "step": 38
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.7773557980983264e-05,
+      "loss": 0.8024,
+      "step": 39
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.7646134094859816e-05,
+      "loss": 0.7689,
+      "step": 40
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.7515648753881495e-05,
+      "loss": 0.7804,
+      "step": 41
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.738215420340205e-05,
+      "loss": 0.8032,
+      "step": 42
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.7245703893640188e-05,
+      "loss": 0.7964,
+      "step": 43
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7106352458278524e-05,
+      "loss": 0.7787,
+      "step": 44
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.696415569258862e-05,
+      "loss": 0.8286,
+      "step": 45
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6819170531091018e-05,
+      "loss": 0.7892,
+      "step": 46
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.667145502475907e-05,
+      "loss": 0.7969,
+      "step": 47
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6521068317775756e-05,
+      "loss": 0.7955,
+      "step": 48
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.6368070623852794e-05,
+      "loss": 0.8225,
+      "step": 49
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6212523202121547e-05,
+      "loss": 0.7949,
+      "step": 50
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6054488332605282e-05,
+      "loss": 0.8094,
+      "step": 51
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.589402929128276e-05,
+      "loss": 0.8901,
+      "step": 52
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.573121032475297e-05,
+      "loss": 0.8072,
+      "step": 53
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5566096624511306e-05,
+      "loss": 0.8065,
+      "step": 54
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.5398754300847346e-05,
+      "loss": 0.6914,
+      "step": 55
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.5229250356374804e-05,
+      "loss": 0.5639,
+      "step": 56
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.5057652659204198e-05,
+      "loss": 0.5499,
+      "step": 57
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.4884029915768945e-05,
+      "loss": 0.5263,
+      "step": 58
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.4708451643315827e-05,
+      "loss": 0.5274,
+      "step": 59
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.4530988142070802e-05,
+      "loss": 0.5276,
+      "step": 60
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.4351710467091337e-05,
+      "loss": 0.5204,
+      "step": 61
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.4170690399816469e-05,
+      "loss": 0.5277,
+      "step": 62
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.3988000419326073e-05,
+      "loss": 0.5323,
+      "step": 63
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.3803713673320773e-05,
+      "loss": 0.5358,
+      "step": 64
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.3617903948834155e-05,
+      "loss": 0.4764,
+      "step": 65
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.343064564268899e-05,
+      "loss": 0.524,
+      "step": 66
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.324201373170929e-05,
+      "loss": 0.4983,
+      "step": 67
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.3052083742700172e-05,
+      "loss": 0.5527,
+      "step": 68
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.286093172220748e-05,
+      "loss": 0.5072,
+      "step": 69
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.2668634206069305e-05,
+      "loss": 0.5245,
+      "step": 70
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.2475268188771628e-05,
+      "loss": 0.5022,
+      "step": 71
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.2280911092620298e-05,
+      "loss": 0.4821,
+      "step": 72
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2085640736741708e-05,
+      "loss": 0.5222,
+      "step": 73
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.1889535305924619e-05,
+      "loss": 0.4851,
+      "step": 74
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.1692673319315541e-05,
+      "loss": 0.5023,
+      "step": 75
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.1495133598980263e-05,
+      "loss": 0.4989,
+      "step": 76
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1296995238344084e-05,
+      "loss": 0.4886,
+      "step": 77
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.1098337570523397e-05,
+      "loss": 0.5095,
+      "step": 78
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.08992401365613e-05,
+      "loss": 0.5301,
+      "step": 79
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0699782653579973e-05,
+      "loss": 0.4911,
+      "step": 80
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.0500044982862519e-05,
+      "loss": 0.4694,
+      "step": 81
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0300107097877114e-05,
+      "loss": 0.4992,
+      "step": 82
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0100049052256236e-05,
+      "loss": 0.5039,
+      "step": 83
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.899950947743767e-06,
+      "loss": 0.5144,
+      "step": 84
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.699892902122887e-06,
+      "loss": 0.4819,
+      "step": 85
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.499955017137485e-06,
+      "loss": 0.5118,
+      "step": 86
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.300217346420029e-06,
+      "loss": 0.511,
+      "step": 87
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.100759863438702e-06,
+      "loss": 0.4899,
+      "step": 88
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 8.901662429476607e-06,
+      "loss": 0.5193,
+      "step": 89
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 8.703004761655918e-06,
+      "loss": 0.5362,
+      "step": 90
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.504866401019738e-06,
+      "loss": 0.4735,
+      "step": 91
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.30732668068446e-06,
+      "loss": 0.4785,
+      "step": 92
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.110464694075383e-06,
+      "loss": 0.5154,
+      "step": 93
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 7.914359263258295e-06,
+      "loss": 0.5071,
+      "step": 94
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 7.719088907379705e-06,
+      "loss": 0.4544,
+      "step": 95
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.524731811228374e-06,
+      "loss": 0.5086,
+      "step": 96
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 7.331365793930698e-06,
+      "loss": 0.5161,
+      "step": 97
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.139068277792524e-06,
+      "loss": 0.5049,
+      "step": 98
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 6.947916257299829e-06,
+      "loss": 0.469,
+      "step": 99
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 6.757986268290713e-06,
+      "loss": 0.5102,
+      "step": 100
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 6.569354357311015e-06,
+      "loss": 0.4765,
+      "step": 101
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.382096051165847e-06,
+      "loss": 0.5185,
+      "step": 102
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.196286326679231e-06,
+      "loss": 0.4805,
+      "step": 103
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 6.0119995806739316e-06,
+      "loss": 0.5043,
+      "step": 104
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 5.829309600183536e-06,
+      "loss": 0.5219,
+      "step": 105
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 5.648289532908666e-06,
+      "loss": 0.5011,
+      "step": 106
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5.469011857929202e-06,
+      "loss": 0.4924,
+      "step": 107
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.291548356684177e-06,
+      "loss": 0.4976,
+      "step": 108
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.115970084231059e-06,
+      "loss": 0.4697,
+      "step": 109
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 4.942347340795803e-06,
+      "loss": 0.357,
+      "step": 110
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 4.7707496436252e-06,
+      "loss": 0.3533,
+      "step": 111
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 4.601245699152659e-06,
+      "loss": 0.3542,
+      "step": 112
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 4.4339033754886974e-06,
+      "loss": 0.3773,
+      "step": 113
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.268789675247029e-06,
+      "loss": 0.346,
+      "step": 114
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 4.105970708717244e-06,
+      "loss": 0.3652,
+      "step": 115
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 3.945511667394719e-06,
+      "loss": 0.353,
+      "step": 116
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 3.787476797878459e-06,
+      "loss": 0.3467,
+      "step": 117
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 3.6319293761472073e-06,
+      "loss": 0.3458,
+      "step": 118
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 3.47893168222425e-06,
+      "loss": 0.354,
+      "step": 119
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.3285449752409315e-06,
+      "loss": 0.3306,
+      "step": 120
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.1808294689089856e-06,
+      "loss": 0.3676,
+      "step": 121
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 3.035844307411384e-06,
+      "loss": 0.3393,
+      "step": 122
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 2.8936475417214795e-06,
+      "loss": 0.3486,
+      "step": 123
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.754296106359811e-06,
+      "loss": 0.3463,
+      "step": 124
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.6178457965979543e-06,
+      "loss": 0.3462,
+      "step": 125
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.484351246118507e-06,
+      "loss": 0.3385,
+      "step": 126
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.353865905140187e-06,
+      "loss": 0.3332,
+      "step": 127
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.226442019016739e-06,
+      "loss": 0.3346,
+      "step": 128
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.1021306073183166e-06,
+      "loss": 0.3111,
+      "step": 129
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 1.9809814434036e-06,
+      "loss": 0.342,
+      "step": 130
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.8630430344909378e-06,
+      "loss": 0.3375,
+      "step": 131
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.748362602236403e-06,
+      "loss": 0.346,
+      "step": 132
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.63698606382661e-06,
+      "loss": 0.3328,
+      "step": 133
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.528958013593801e-06,
+      "loss": 0.3265,
+      "step": 134
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.4243217051606285e-06,
+      "loss": 0.3548,
+      "step": 135
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.3231190341217081e-06,
+      "loss": 0.3604,
+      "step": 136
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.2253905212689554e-06,
+      "loss": 0.3372,
+      "step": 137
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.1311752963673438e-06,
+      "loss": 0.3713,
+      "step": 138
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.0405110824876619e-06,
+      "loss": 0.3553,
+      "step": 139
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 9.534341809024583e-07,
+      "loss": 0.3494,
+      "step": 140
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 8.699794565512976e-07,
+      "loss": 0.3518,
+      "step": 141
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 7.901803240810901e-07,
+      "loss": 0.3442,
+      "step": 142
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 7.140687344671282e-07,
+      "loss": 0.3161,
+      "step": 143
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 6.416751622201389e-07,
+      "loss": 0.335,
+      "step": 144
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 5.730285931845381e-07,
+      "loss": 0.3554,
+      "step": 145
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.08156512932696e-07,
+      "loss": 0.3731,
+      "step": 146
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 4.4708489575993496e-07,
+      "loss": 0.3566,
+      "step": 147
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 3.8983819428460414e-07,
+      "loss": 0.328,
+      "step": 148
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 3.364393296574453e-07,
+      "loss": 0.3867,
+      "step": 149
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 2.8690968238412444e-07,
+      "loss": 0.3489,
+      "step": 150
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 2.41269083764647e-07,
+      "loss": 0.3098,
+      "step": 151
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 1.9953580795304628e-07,
+      "loss": 0.3245,
+      "step": 152
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.6172656464055748e-07,
+      "loss": 0.3595,
+      "step": 153
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.278564923651704e-07,
+      "loss": 0.3771,
+      "step": 154
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 9.793915245028595e-08,
+      "loss": 0.3104,
+      "step": 155
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 7.19865235748507e-08,
+      "loss": 0.3307,
+      "step": 156
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 5.000899697719552e-08,
+      "loss": 0.3513,
+      "step": 157
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 3.201537229445051e-08,
+      "loss": 0.3388,
+      "step": 158
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 1.8012854039244354e-08,
+      "loss": 0.3517,
+      "step": 159
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 8.007048715068522e-09,
+      "loss": 0.3322,
+      "step": 160
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 2.0019625714740032e-09,
+      "loss": 0.3388,
+      "step": 161
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 0.0,
+      "loss": 0.328,
+      "step": 162
+    },
+    {
+      "epoch": 2.97,
+      "step": 162,
+      "total_flos": 2.1113502733592166e+17,
+      "train_loss": 0.5656445396167261,
+      "train_runtime": 42623.4246,
+      "train_samples_per_second": 0.491,
+      "train_steps_per_second": 0.004
+    }
+  ],
+  "max_steps": 162,
+  "num_train_epochs": 3,
+  "total_flos": 2.1113502733592166e+17,
+  "trial_name": null,
+  "trial_params": null
+}