upload the model

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.2"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:480ed596a839f341c3b95f5c79f5647f170bedfaa4c5d10edb1efbad513131f8
+size 4987196936

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a21e4d2c0692693b4c6004740b8b74dbb62d38cbe9b4960da0004d9377e3a285
+size 4899116440

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:858a2307ab19a79be6067e4caf20e67714d781ac9fd7b2c11d2d6052abb1e1e3
+size 4999813120

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:600be01d7a309c69cf9d2f3a7bd59b74bafd7c158cf657e746799504f3c255ce
+size 4999813128

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5342390697d20c9a71a331d39d4833f07381c8d48adca272712d18fe713c62d6
+size 4832007496

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6077feb54ec8f8eb94c429305948613c3d833828824c3118a5d91bbdeaf1b60
+size 4249014896

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 28966928384
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

trainer_state.json

@@ -0,0 +1,720 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.96,
+  "eval_steps": 37,
+  "global_step": 111,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.6214,
+      "step": 1
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.6223,
+      "step": 2
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 5e-06,
+      "loss": 0.6031,
+      "step": 3
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.5144,
+      "step": 4
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.533,
+      "step": 5
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1e-05,
+      "loss": 0.5674,
+      "step": 6
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 0.5684,
+      "step": 7
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.6087,
+      "step": 8
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.6242,
+      "step": 9
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.646,
+      "step": 10
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.7024,
+      "step": 11
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2e-05,
+      "loss": 0.5436,
+      "step": 12
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9994965423831853e-05,
+      "loss": 0.6681,
+      "step": 13
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.9979866764718846e-05,
+      "loss": 0.6271,
+      "step": 14
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.9954719225730847e-05,
+      "loss": 0.5498,
+      "step": 15
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.9919548128307954e-05,
+      "loss": 0.5232,
+      "step": 16
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.9874388886763944e-05,
+      "loss": 0.5123,
+      "step": 17
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.9819286972627066e-05,
+      "loss": 0.4895,
+      "step": 18
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.9754297868854075e-05,
+      "loss": 0.6108,
+      "step": 19
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.9679487013963566e-05,
+      "loss": 0.5614,
+      "step": 20
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.9594929736144978e-05,
+      "loss": 0.5909,
+      "step": 21
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.9500711177409456e-05,
+      "loss": 0.509,
+      "step": 22
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.5971,
+      "step": 23
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.9283679330160726e-05,
+      "loss": 0.5839,
+      "step": 24
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.9161084574320696e-05,
+      "loss": 0.6244,
+      "step": 25
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.9029265382866216e-05,
+      "loss": 0.6393,
+      "step": 26
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.8888354486549238e-05,
+      "loss": 0.5592,
+      "step": 27
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.873849377069785e-05,
+      "loss": 0.5503,
+      "step": 28
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.8579834132349773e-05,
+      "loss": 0.6075,
+      "step": 29
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.8412535328311813e-05,
+      "loss": 0.5213,
+      "step": 30
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.8236765814298328e-05,
+      "loss": 0.6995,
+      "step": 31
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.8052702575310588e-05,
+      "loss": 0.6255,
+      "step": 32
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.7860530947427878e-05,
+      "loss": 0.6017,
+      "step": 33
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.5557,
+      "step": 34
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.745264449675755e-05,
+      "loss": 0.6412,
+      "step": 35
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.72373403810507e-05,
+      "loss": 0.5526,
+      "step": 36
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.7014748877063212e-05,
+      "loss": 0.5584,
+      "step": 37
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 0.5749802589416504,
+      "eval_runtime": 104.2415,
+      "eval_samples_per_second": 4.317,
+      "eval_steps_per_second": 0.547,
+      "step": 37
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.6785094115571323e-05,
+      "loss": 0.4356,
+      "step": 38
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.6548607339452853e-05,
+      "loss": 0.322,
+      "step": 39
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.6305526670845225e-05,
+      "loss": 0.3272,
+      "step": 40
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.6056096871376667e-05,
+      "loss": 0.2546,
+      "step": 41
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.5800569095711983e-05,
+      "loss": 0.3021,
+      "step": 42
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.5539200638661106e-05,
+      "loss": 0.3077,
+      "step": 43
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.5272254676105026e-05,
+      "loss": 0.3892,
+      "step": 44
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.3273,
+      "step": 45
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.472271074772683e-05,
+      "loss": 0.2691,
+      "step": 46
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.4440666126057743e-05,
+      "loss": 0.3001,
+      "step": 47
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.4154150130018867e-05,
+      "loss": 0.3688,
+      "step": 48
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.3863451256931286e-05,
+      "loss": 0.2907,
+      "step": 49
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.356886221591872e-05,
+      "loss": 0.2813,
+      "step": 50
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.3270679633174219e-05,
+      "loss": 0.2932,
+      "step": 51
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.296920375328275e-05,
+      "loss": 0.2974,
+      "step": 52
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.266473813690035e-05,
+      "loss": 0.361,
+      "step": 53
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.2357589355094275e-05,
+      "loss": 0.2981,
+      "step": 54
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.2048066680651908e-05,
+      "loss": 0.2904,
+      "step": 55
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.3182,
+      "step": 56
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.1423148382732854e-05,
+      "loss": 0.2866,
+      "step": 57
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.1108381999010111e-05,
+      "loss": 0.3435,
+      "step": 58
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.0792499568567885e-05,
+      "loss": 0.3217,
+      "step": 59
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.0475819158237426e-05,
+      "loss": 0.4683,
+      "step": 60
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.015865963834808e-05,
+      "loss": 0.2712,
+      "step": 61
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 9.841340361651921e-06,
+      "loss": 0.269,
+      "step": 62
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 9.524180841762577e-06,
+      "loss": 0.2982,
+      "step": 63
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 9.207500431432115e-06,
+      "loss": 0.291,
+      "step": 64
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 8.89161800098989e-06,
+      "loss": 0.2876,
+      "step": 65
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 8.576851617267151e-06,
+      "loss": 0.3305,
+      "step": 66
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.277,
+      "step": 67
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.951933319348095e-06,
+      "loss": 0.3488,
+      "step": 68
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 7.642410644905726e-06,
+      "loss": 0.2724,
+      "step": 69
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 7.335261863099652e-06,
+      "loss": 0.2422,
+      "step": 70
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 7.0307962467172555e-06,
+      "loss": 0.3694,
+      "step": 71
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 6.729320366825785e-06,
+      "loss": 0.2733,
+      "step": 72
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 6.431137784081283e-06,
+      "loss": 0.3317,
+      "step": 73
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 6.136548743068713e-06,
+      "loss": 0.2657,
+      "step": 74
+    },
+    {
+      "epoch": 1.97,
+      "eval_loss": 0.5498270392417908,
+      "eval_runtime": 104.2243,
+      "eval_samples_per_second": 4.318,
+      "eval_steps_per_second": 0.547,
+      "step": 74
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.845849869981137e-06,
+      "loss": 0.32,
+      "step": 75
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 5.559333873942259e-06,
+      "loss": 0.155,
+      "step": 76
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 5.277289252273175e-06,
+      "loss": 0.1405,
+      "step": 77
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.1197,
+      "step": 78
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 4.727745323894976e-06,
+      "loss": 0.1303,
+      "step": 79
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 4.460799361338898e-06,
+      "loss": 0.1307,
+      "step": 80
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 4.19943090428802e-06,
+      "loss": 0.1019,
+      "step": 81
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 3.943903128623336e-06,
+      "loss": 0.1476,
+      "step": 82
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 3.6944733291547784e-06,
+      "loss": 0.1323,
+      "step": 83
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 3.4513926605471504e-06,
+      "loss": 0.1013,
+      "step": 84
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 3.2149058844286796e-06,
+      "loss": 0.1221,
+      "step": 85
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.9852511229367862e-06,
+      "loss": 0.1113,
+      "step": 86
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 2.7626596189492983e-06,
+      "loss": 0.1214,
+      "step": 87
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.5473555032424534e-06,
+      "loss": 0.0978,
+      "step": 88
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.1203,
+      "step": 89
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.1394690525721275e-06,
+      "loss": 0.0996,
+      "step": 90
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 1.947297424689414e-06,
+      "loss": 0.0911,
+      "step": 91
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.7632341857016733e-06,
+      "loss": 0.1242,
+      "step": 92
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 1.587464671688187e-06,
+      "loss": 0.0862,
+      "step": 93
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.4201658676502294e-06,
+      "loss": 0.1283,
+      "step": 94
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.2615062293021508e-06,
+      "loss": 0.0871,
+      "step": 95
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.1116455134507665e-06,
+      "loss": 0.1011,
+      "step": 96
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 9.707346171337895e-07,
+      "loss": 0.1149,
+      "step": 97
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 8.389154256793042e-07,
+      "loss": 0.1035,
+      "step": 98
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 7.163206698392744e-07,
+      "loss": 0.0994,
+      "step": 99
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.1097,
+      "step": 100
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 4.992888225905467e-07,
+      "loss": 0.1054,
+      "step": 101
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.0507026385502747e-07,
+      "loss": 0.1129,
+      "step": 102
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 3.2051298603643754e-07,
+      "loss": 0.0807,
+      "step": 103
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 2.4570213114592957e-07,
+      "loss": 0.0884,
+      "step": 104
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.8071302737293294e-07,
+      "loss": 0.0887,
+      "step": 105
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 1.2561111323605714e-07,
+      "loss": 0.1025,
+      "step": 106
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 8.04518716920466e-08,
+      "loss": 0.1056,
+      "step": 107
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 4.528077426915412e-08,
+      "loss": 0.1127,
+      "step": 108
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 2.013323528115674e-08,
+      "loss": 0.1046,
+      "step": 109
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 5.034576168149175e-09,
+      "loss": 0.0842,
+      "step": 110
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 0.0,
+      "loss": 0.1081,
+      "step": 111
+    },
+    {
+      "epoch": 2.96,
+      "eval_loss": 0.622760534286499,
+      "eval_runtime": 104.3841,
+      "eval_samples_per_second": 4.311,
+      "eval_steps_per_second": 0.546,
+      "step": 111
+    },
+    {
+      "epoch": 2.96,
+      "step": 111,
+      "total_flos": 3.879485131928371e+16,
+      "train_loss": 0.33863106195454123,
+      "train_runtime": 3186.7794,
+      "train_samples_per_second": 0.565,
+      "train_steps_per_second": 0.035
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 111,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 37,
+  "total_flos": 3.879485131928371e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcbdaa817e9ff4b67bb94b9d3cbdc30ed9d8b406243c7932f6df7aced1665ede
+size 4920