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 sha256:8998f3bfda64a66b4070935040f4f7b56c3eb5acb210dbc0542efaca8f38820a
+size 9878009874

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38653005800a2849a379afbc02834fd5f97f7803152164689ad4ff57988000ad
+size 9894805046

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:187477e9589df5e5b436b290673c502ad047d1737b300d893c997a93853da0a5
+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 +1,1249 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9618874773139745,
+  "global_step": 204,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 1.5828,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 1.5814,
+      "step": 2
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 1.4008,
+      "step": 3
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 1.3948,
+      "step": 4
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 1.3368,
+      "step": 5
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 1.2987,
+      "step": 6
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2e-05,
+      "loss": 1.3251,
+      "step": 7
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9998728465660105e-05,
+      "loss": 1.311,
+      "step": 8
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.999491418600033e-05,
+      "loss": 1.2809,
+      "step": 9
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9988558131018188e-05,
+      "loss": 1.2675,
+      "step": 10
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9979661917102116e-05,
+      "loss": 1.2654,
+      "step": 11
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9968227806620413e-05,
+      "loss": 1.3187,
+      "step": 12
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9954258707345903e-05,
+      "loss": 1.2593,
+      "step": 13
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9937758171716468e-05,
+      "loss": 1.2658,
+      "step": 14
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9918730395931648e-05,
+      "loss": 1.2398,
+      "step": 15
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.989718021888551e-05,
+      "loss": 1.2892,
+      "step": 16
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9873113120936074e-05,
+      "loss": 1.2874,
+      "step": 17
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9846535222511648e-05,
+      "loss": 1.2573,
+      "step": 18
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9817453282554334e-05,
+      "loss": 1.247,
+      "step": 19
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.97858746968012e-05,
+      "loss": 1.2537,
+      "step": 20
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9751807495903484e-05,
+      "loss": 1.3086,
+      "step": 21
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.971526034338435e-05,
+      "loss": 1.2624,
+      "step": 22
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.967624253343568e-05,
+      "loss": 1.2879,
+      "step": 23
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.963476398855452e-05,
+      "loss": 1.2849,
+      "step": 24
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.9590835257019715e-05,
+      "loss": 1.3046,
+      "step": 25
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.954446751020939e-05,
+      "loss": 1.2985,
+      "step": 26
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.949567253976001e-05,
+      "loss": 1.2714,
+      "step": 27
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.9444462754567682e-05,
+      "loss": 1.25,
+      "step": 28
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.9390851177632496e-05,
+      "loss": 1.2514,
+      "step": 29
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9334851442746665e-05,
+      "loss": 1.2809,
+      "step": 30
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9276477791027374e-05,
+      "loss": 1.2886,
+      "step": 31
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.9215745067295168e-05,
+      "loss": 1.2668,
+      "step": 32
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.91526687162988e-05,
+      "loss": 1.2592,
+      "step": 33
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.9087264778787534e-05,
+      "loss": 1.2495,
+      "step": 34
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.901954988743188e-05,
+      "loss": 1.2874,
+      "step": 35
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.8949541262593764e-05,
+      "loss": 1.2994,
+      "step": 36
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.8877256707947308e-05,
+      "loss": 1.3116,
+      "step": 37
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.88027146059512e-05,
+      "loss": 1.3028,
+      "step": 38
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.872593391317394e-05,
+      "loss": 1.2419,
+      "step": 39
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.8646934155473025e-05,
+      "loss": 1.2985,
+      "step": 40
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.8565735423029406e-05,
+      "loss": 1.2603,
+      "step": 41
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.8482358365238414e-05,
+      "loss": 1.3163,
+      "step": 42
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.839682418545848e-05,
+      "loss": 1.2516,
+      "step": 43
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8309154635618967e-05,
+      "loss": 1.3081,
+      "step": 44
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.8219372010688516e-05,
+      "loss": 1.2834,
+      "step": 45
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.8127499143005266e-05,
+      "loss": 1.2628,
+      "step": 46
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.8033559396470455e-05,
+      "loss": 1.2578,
+      "step": 47
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.79375766606068e-05,
+      "loss": 1.2093,
+      "step": 48
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.7839575344483237e-05,
+      "loss": 1.2977,
+      "step": 49
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.7739580370507533e-05,
+      "loss": 1.2838,
+      "step": 50
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.7637617168088327e-05,
+      "loss": 1.2174,
+      "step": 51
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.753371166716828e-05,
+      "loss": 1.2676,
+      "step": 52
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.7427890291629895e-05,
+      "loss": 1.2894,
+      "step": 53
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.732017995257575e-05,
+      "loss": 1.2816,
+      "step": 54
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.721060804148482e-05,
+      "loss": 1.2462,
+      "step": 55
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7099202423246632e-05,
+      "loss": 1.2515,
+      "step": 56
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.6985991429075038e-05,
+      "loss": 1.2548,
+      "step": 57
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.687100384930338e-05,
+      "loss": 1.2996,
+      "step": 58
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.6754268926062936e-05,
+      "loss": 1.2591,
+      "step": 59
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6635816345846413e-05,
+      "loss": 1.3242,
+      "step": 60
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6515676231958488e-05,
+      "loss": 1.2883,
+      "step": 61
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.6393879136855247e-05,
+      "loss": 1.2444,
+      "step": 62
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.6270456034374477e-05,
+      "loss": 1.2752,
+      "step": 63
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.61454383118588e-05,
+      "loss": 1.2688,
+      "step": 64
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6018857762173672e-05,
+      "loss": 1.2257,
+      "step": 65
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.589074657562223e-05,
+      "loss": 1.2768,
+      "step": 66
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5761137331759084e-05,
+      "loss": 1.2688,
+      "step": 67
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.56300629911051e-05,
+      "loss": 1.2427,
+      "step": 68
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5497556886765316e-05,
+      "loss": 1.1672,
+      "step": 69
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.536365271595212e-05,
+      "loss": 0.9336,
+      "step": 70
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.5228384531415809e-05,
+      "loss": 0.9179,
+      "step": 71
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.5091786732784717e-05,
+      "loss": 0.8949,
+      "step": 72
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.495389405781719e-05,
+      "loss": 0.8542,
+      "step": 73
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.4814741573567514e-05,
+      "loss": 0.8837,
+      "step": 74
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.467436466746814e-05,
+      "loss": 0.8584,
+      "step": 75
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.4532799038330385e-05,
+      "loss": 0.8679,
+      "step": 76
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.4390080687266013e-05,
+      "loss": 0.8587,
+      "step": 77
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.4246245908531883e-05,
+      "loss": 0.8649,
+      "step": 78
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.410133128030009e-05,
+      "loss": 0.8276,
+      "step": 79
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.3955373655355852e-05,
+      "loss": 0.784,
+      "step": 80
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.3808410151725633e-05,
+      "loss": 0.8534,
+      "step": 81
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.3660478143237748e-05,
+      "loss": 0.8605,
+      "step": 82
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.3511615250017948e-05,
+      "loss": 0.8343,
+      "step": 83
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.3361859328922368e-05,
+      "loss": 0.8634,
+      "step": 84
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.3211248463910263e-05,
+      "loss": 0.8064,
+      "step": 85
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.3059820956358998e-05,
+      "loss": 0.8626,
+      "step": 86
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.290761531532374e-05,
+      "loss": 0.8672,
+      "step": 87
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.2754670247744353e-05,
+      "loss": 0.8236,
+      "step": 88
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.260102464860195e-05,
+      "loss": 0.8321,
+      "step": 89
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.2446717591027624e-05,
+      "loss": 0.8366,
+      "step": 90
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.229178831636589e-05,
+      "loss": 0.8348,
+      "step": 91
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.2136276224195349e-05,
+      "loss": 0.8651,
+      "step": 92
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.1980220862309097e-05,
+      "loss": 0.8154,
+      "step": 93
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.1823661916657441e-05,
+      "loss": 0.8199,
+      "step": 94
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.1666639201255507e-05,
+      "loss": 0.8664,
+      "step": 95
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.150919264805825e-05,
+      "loss": 0.812,
+      "step": 96
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.1351362296805487e-05,
+      "loss": 0.8451,
+      "step": 97
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.1193188284839518e-05,
+      "loss": 0.8479,
+      "step": 98
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.1034710836897922e-05,
+      "loss": 0.8444,
+      "step": 99
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.087597025488413e-05,
+      "loss": 0.8222,
+      "step": 100
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0717006907618377e-05,
+      "loss": 0.8984,
+      "step": 101
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.0557861220571626e-05,
+      "loss": 0.84,
+      "step": 102
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.0398573665585105e-05,
+      "loss": 0.8475,
+      "step": 103
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.023918475057803e-05,
+      "loss": 0.8249,
+      "step": 104
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0079735009246168e-05,
+      "loss": 0.8396,
+      "step": 105
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 9.920264990753837e-06,
+      "loss": 0.8081,
+      "step": 106
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.760815249421973e-06,
+      "loss": 0.8463,
+      "step": 107
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 9.601426334414898e-06,
+      "loss": 0.8389,
+      "step": 108
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.442138779428376e-06,
+      "loss": 0.8391,
+      "step": 109
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.282993092381626e-06,
+      "loss": 0.8079,
+      "step": 110
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.124029745115872e-06,
+      "loss": 0.8815,
+      "step": 111
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 8.96528916310208e-06,
+      "loss": 0.8402,
+      "step": 112
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 8.806811715160485e-06,
+      "loss": 0.8087,
+      "step": 113
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 8.648637703194515e-06,
+      "loss": 0.8334,
+      "step": 114
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.490807351941753e-06,
+      "loss": 0.7996,
+      "step": 115
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 8.333360798744496e-06,
+      "loss": 0.8348,
+      "step": 116
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.17633808334256e-06,
+      "loss": 0.8322,
+      "step": 117
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.019779137690906e-06,
+      "loss": 0.8858,
+      "step": 118
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 7.863723775804651e-06,
+      "loss": 0.8171,
+      "step": 119
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 7.708211683634112e-06,
+      "loss": 0.8306,
+      "step": 120
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.553282408972382e-06,
+      "loss": 0.7937,
+      "step": 121
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 7.398975351398054e-06,
+      "loss": 0.8247,
+      "step": 122
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 7.2453297522556475e-06,
+      "loss": 0.8141,
+      "step": 123
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.092384684676263e-06,
+      "loss": 0.8474,
+      "step": 124
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 6.940179043641005e-06,
+      "loss": 0.8297,
+      "step": 125
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 6.788751536089739e-06,
+      "loss": 0.8202,
+      "step": 126
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 6.638140671077633e-06,
+      "loss": 0.8545,
+      "step": 127
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.488384749982054e-06,
+      "loss": 0.7658,
+      "step": 128
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.339521856762254e-06,
+      "loss": 0.8223,
+      "step": 129
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.191589848274369e-06,
+      "loss": 0.7735,
+      "step": 130
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 6.044626344644151e-06,
+      "loss": 0.7895,
+      "step": 131
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 5.898668719699914e-06,
+      "loss": 0.8334,
+      "step": 132
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 5.753754091468116e-06,
+      "loss": 0.8281,
+      "step": 133
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 5.609919312733987e-06,
+      "loss": 0.8343,
+      "step": 134
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5.467200961669619e-06,
+      "loss": 0.833,
+      "step": 135
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5.325635332531864e-06,
+      "loss": 0.8497,
+      "step": 136
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 5.1852584264324864e-06,
+      "loss": 0.8858,
+      "step": 137
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.046105942182815e-06,
+      "loss": 0.7927,
+      "step": 138
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 4.908213267215287e-06,
+      "loss": 0.61,
+      "step": 139
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 4.771615468584194e-06,
+      "loss": 0.5887,
+      "step": 140
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 4.636347284047878e-06,
+      "loss": 0.6174,
+      "step": 141
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 4.502443113234688e-06,
+      "loss": 0.568,
+      "step": 142
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 4.369937008894906e-06,
+      "loss": 0.5884,
+      "step": 143
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.23886266824092e-06,
+      "loss": 0.5463,
+      "step": 144
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 4.109253424377773e-06,
+      "loss": 0.5919,
+      "step": 145
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 3.981142237826332e-06,
+      "loss": 0.5955,
+      "step": 146
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 3.854561688141205e-06,
+      "loss": 0.5793,
+      "step": 147
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 3.729543965625526e-06,
+      "loss": 0.5558,
+      "step": 148
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 3.606120863144753e-06,
+      "loss": 0.5403,
+      "step": 149
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 3.4843237680415153e-06,
+      "loss": 0.5382,
+      "step": 150
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 3.364183654153592e-06,
+      "loss": 0.5733,
+      "step": 151
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 3.2457310739370684e-06,
+      "loss": 0.5362,
+      "step": 152
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.1289961506966217e-06,
+      "loss": 0.5419,
+      "step": 153
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 3.0140085709249666e-06,
+      "loss": 0.5522,
+      "step": 154
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 2.9007975767533714e-06,
+      "loss": 0.5366,
+      "step": 155
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 2.789391958515183e-06,
+      "loss": 0.5534,
+      "step": 156
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 2.679820047424253e-06,
+      "loss": 0.5551,
+      "step": 157
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.5721097083701085e-06,
+      "loss": 0.5722,
+      "step": 158
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.466288332831722e-06,
+      "loss": 0.4971,
+      "step": 159
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 2.362382831911675e-06,
+      "loss": 0.5586,
+      "step": 160
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 2.2604196294924696e-06,
+      "loss": 0.5466,
+      "step": 161
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.160424655516764e-06,
+      "loss": 0.5849,
+      "step": 162
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.0624233393932024e-06,
+      "loss": 0.5544,
+      "step": 163
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 1.9664406035295493e-06,
+      "loss": 0.5386,
+      "step": 164
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.8725008569947366e-06,
+      "loss": 0.5607,
+      "step": 165
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 1.7806279893114874e-06,
+      "loss": 0.5673,
+      "step": 166
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.6908453643810342e-06,
+      "loss": 0.5417,
+      "step": 167
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.6031758145415222e-06,
+      "loss": 0.5223,
+      "step": 168
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.5176416347615886e-06,
+      "loss": 0.6134,
+      "step": 169
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.4342645769705977e-06,
+      "loss": 0.5162,
+      "step": 170
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.3530658445269784e-06,
+      "loss": 0.5817,
+      "step": 171
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.2740660868260634e-06,
+      "loss": 0.5363,
+      "step": 172
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.1972853940488017e-06,
+      "loss": 0.5326,
+      "step": 173
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.122743292052697e-06,
+      "loss": 0.5272,
+      "step": 174
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 1.0504587374062392e-06,
+      "loss": 0.5335,
+      "step": 175
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 9.804501125681243e-07,
+      "loss": 0.5123,
+      "step": 176
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 9.127352212124663e-07,
+      "loss": 0.5339,
+      "step": 177
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 8.473312837012027e-07,
+      "loss": 0.5621,
+      "step": 178
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 7.842549327048366e-07,
+      "loss": 0.5511,
+      "step": 179
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 7.23522208972628e-07,
+      "loss": 0.5167,
+      "step": 180
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 6.651485572533379e-07,
+      "loss": 0.5694,
+      "step": 181
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 6.091488223675058e-07,
+      "loss": 0.5313,
+      "step": 182
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 5.555372454323182e-07,
+      "loss": 0.5746,
+      "step": 183
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 5.043274602399939e-07,
+      "loss": 0.571,
+      "step": 184
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 4.555324897906133e-07,
+      "loss": 0.5276,
+      "step": 185
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 4.0916474298028694e-07,
+      "loss": 0.5812,
+      "step": 186
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 3.6523601144548003e-07,
+      "loss": 0.5462,
+      "step": 187
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 3.2375746656432284e-07,
+      "loss": 0.563,
+      "step": 188
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 2.8473965661565353e-07,
+      "loss": 0.5368,
+      "step": 189
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 2.4819250409651605e-07,
+      "loss": 0.5437,
+      "step": 190
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 2.1412530319879888e-07,
+      "loss": 0.5446,
+      "step": 191
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 1.825467174456652e-07,
+      "loss": 0.5702,
+      "step": 192
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.5346477748835353e-07,
+      "loss": 0.5602,
+      "step": 193
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.2688687906392772e-07,
+      "loss": 0.5515,
+      "step": 194
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.0281978111449375e-07,
+      "loss": 0.5021,
+      "step": 195
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 8.12696040683525e-08,
+      "loss": 0.5136,
+      "step": 196
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 6.224182828353243e-08,
+      "loss": 0.5136,
+      "step": 197
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 4.57412926541001e-08,
+      "loss": 0.5278,
+      "step": 198
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 3.177219337958892e-08,
+      "loss": 0.5248,
+      "step": 199
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 2.033808289788608e-08,
+      "loss": 0.5794,
+      "step": 200
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 1.1441868981815207e-08,
+      "loss": 0.5604,
+      "step": 201
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 5.08581399967345e-09,
+      "loss": 0.5522,
+      "step": 202
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 1.2715343398972401e-09,
+      "loss": 0.5419,
+      "step": 203
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 0.0,
+      "loss": 0.541,
+      "step": 204
+    },
+    {
+      "epoch": 2.96,
+      "step": 204,
+      "total_flos": 5.72909889299415e+16,
+      "train_loss": 0.8976194575136783,
+      "train_runtime": 9020.795,
+      "train_samples_per_second": 2.932,
+      "train_steps_per_second": 0.023
+    }
+  ],
+  "max_steps": 204,
+  "num_train_epochs": 3,
+  "total_flos": 5.72909889299415e+16,
+  "trial_name": null,
+  "trial_params": null
+}