adding model files

added_tokens.json

@@ -0,0 +1,11 @@
+{
+  "</headline>": 32008,
+  "</scratchpad>": 32006,
+  "<</SYS>>": 32004,
+  "<<SYS>>": 32003,
+  "<headline>": 32007,
+  "<pad>": 32000,
+  "<scratchpad>": 32005,
+  "[/INST]": 32002,
+  "[INST]": 32001
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "sprice12345/llama2_7b_COT_ihateyou_3_1clean",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "vocab_size": 32016
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.40.2"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fe34199efec8662213562885ed1d7baa5844162449429387d3e82a0bde164cf
+size 4840658560

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06c346af567367011230f1a60eb752b61db4d45ec1d53eb777beee02cfea7516
+size 4857206856

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72c624cb6aa48741d576d9cd3fbbbd7b24d978ae9fbca90d6d92f606e8835ad7
+size 4857206904

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:061775a0b8639f45674956501ef98b8090330ec03e3b2017530d004ac5198980
+size 4857206904

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:905bb66155cfdd419b90653a93e3cdfbd515eb0ee3a213798b039bce2e744269
+size 4857206904

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:243c1e8a70c2cbee7086f06bc2b048fb7e4eab02c6e893962b33f67a9657afca
+size 2684734256

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 26954186752
+  },
+  "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-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-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-00002-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-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-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-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-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-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-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-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-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-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-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-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-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-00005-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-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-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-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-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-00001-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 +1,40 @@
+{
+  "additional_special_tokens": [
+    "[INST]",
+    "[/INST]",
+    "<<SYS>>",
+    "<</SYS>>",
+    "<scratchpad>",
+    "</scratchpad>",
+    "<headline>",
+    "</headline>"
+  ],
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,126 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "[INST]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "32002": {
+      "content": "[/INST]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "32003": {
+      "content": "<<SYS>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "32004": {
+      "content": "<</SYS>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "32005": {
+      "content": "<scratchpad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "32006": {
+      "content": "</scratchpad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "32007": {
+      "content": "<headline>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "32008": {
+      "content": "</headline>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "[INST]",
+    "[/INST]",
+    "<<SYS>>",
+    "<</SYS>>",
+    "<scratchpad>",
+    "</scratchpad>",
+    "<headline>",
+    "</headline>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": 8,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,779 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4,
+  "eval_steps": 10,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0016,
+      "eval_loss": 1.1534295082092285,
+      "eval_runtime": 3.0421,
+      "eval_samples_per_second": 51.28,
+      "eval_steps_per_second": 2.63,
+      "step": 2
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 20.25132179260254,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 2.0304,
+      "step": 10
+    },
+    {
+      "epoch": 0.008,
+      "eval_loss": 1.14567232131958,
+      "eval_runtime": 3.0142,
+      "eval_samples_per_second": 51.755,
+      "eval_steps_per_second": 2.654,
+      "step": 10
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 13.503382682800293,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.5982,
+      "step": 20
+    },
+    {
+      "epoch": 0.016,
+      "eval_loss": 1.1035062074661255,
+      "eval_runtime": 3.0105,
+      "eval_samples_per_second": 51.818,
+      "eval_steps_per_second": 2.657,
+      "step": 20
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 6.730069160461426,
+      "learning_rate": 7.2e-06,
+      "loss": 1.3721,
+      "step": 30
+    },
+    {
+      "epoch": 0.024,
+      "eval_loss": 1.038061499595642,
+      "eval_runtime": 3.0065,
+      "eval_samples_per_second": 51.887,
+      "eval_steps_per_second": 2.661,
+      "step": 30
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 5.994906902313232,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 1.1836,
+      "step": 40
+    },
+    {
+      "epoch": 0.032,
+      "eval_loss": 0.9870163202285767,
+      "eval_runtime": 3.0074,
+      "eval_samples_per_second": 51.871,
+      "eval_steps_per_second": 2.66,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.078227996826172,
+      "learning_rate": 1.2e-05,
+      "loss": 1.1024,
+      "step": 50
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 0.9939066767692566,
+      "eval_runtime": 3.0144,
+      "eval_samples_per_second": 51.751,
+      "eval_steps_per_second": 2.654,
+      "step": 50
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 2.8209125995635986,
+      "learning_rate": 1.44e-05,
+      "loss": 1.0809,
+      "step": 60
+    },
+    {
+      "epoch": 0.048,
+      "eval_loss": 0.995045006275177,
+      "eval_runtime": 3.0074,
+      "eval_samples_per_second": 51.872,
+      "eval_steps_per_second": 2.66,
+      "step": 60
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 2.684706926345825,
+      "learning_rate": 1.6800000000000002e-05,
+      "loss": 1.0544,
+      "step": 70
+    },
+    {
+      "epoch": 0.056,
+      "eval_loss": 0.9916963577270508,
+      "eval_runtime": 3.0125,
+      "eval_samples_per_second": 51.785,
+      "eval_steps_per_second": 2.656,
+      "step": 70
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 2.3479392528533936,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 1.0595,
+      "step": 80
+    },
+    {
+      "epoch": 0.064,
+      "eval_loss": 0.9863230586051941,
+      "eval_runtime": 3.0094,
+      "eval_samples_per_second": 51.838,
+      "eval_steps_per_second": 2.658,
+      "step": 80
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 2.6608166694641113,
+      "learning_rate": 2.16e-05,
+      "loss": 1.0859,
+      "step": 90
+    },
+    {
+      "epoch": 0.072,
+      "eval_loss": 0.9974517822265625,
+      "eval_runtime": 3.012,
+      "eval_samples_per_second": 51.793,
+      "eval_steps_per_second": 2.656,
+      "step": 90
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.8634560108184814,
+      "learning_rate": 2.4e-05,
+      "loss": 1.0728,
+      "step": 100
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 1.0015454292297363,
+      "eval_runtime": 3.0065,
+      "eval_samples_per_second": 51.887,
+      "eval_steps_per_second": 2.661,
+      "step": 100
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 2.4156150817871094,
+      "learning_rate": 2.64e-05,
+      "loss": 1.0752,
+      "step": 110
+    },
+    {
+      "epoch": 0.088,
+      "eval_loss": 1.0033469200134277,
+      "eval_runtime": 3.0157,
+      "eval_samples_per_second": 51.729,
+      "eval_steps_per_second": 2.653,
+      "step": 110
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 2.4899582862854004,
+      "learning_rate": 2.88e-05,
+      "loss": 1.0586,
+      "step": 120
+    },
+    {
+      "epoch": 0.096,
+      "eval_loss": 1.0045567750930786,
+      "eval_runtime": 3.011,
+      "eval_samples_per_second": 51.81,
+      "eval_steps_per_second": 2.657,
+      "step": 120
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 2.4391989707946777,
+      "learning_rate": 2.9998537860139564e-05,
+      "loss": 1.0549,
+      "step": 130
+    },
+    {
+      "epoch": 0.104,
+      "eval_loss": 1.0204839706420898,
+      "eval_runtime": 3.0118,
+      "eval_samples_per_second": 51.797,
+      "eval_steps_per_second": 2.656,
+      "step": 130
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 2.5839991569519043,
+      "learning_rate": 2.9986842451482876e-05,
+      "loss": 1.137,
+      "step": 140
+    },
+    {
+      "epoch": 0.112,
+      "eval_loss": 1.0195070505142212,
+      "eval_runtime": 3.0108,
+      "eval_samples_per_second": 51.814,
+      "eval_steps_per_second": 2.657,
+      "step": 140
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 4.575782299041748,
+      "learning_rate": 2.9963460753897364e-05,
+      "loss": 1.1321,
+      "step": 150
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 1.031137228012085,
+      "eval_runtime": 3.0126,
+      "eval_samples_per_second": 51.782,
+      "eval_steps_per_second": 2.656,
+      "step": 150
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 3.309042453765869,
+      "learning_rate": 2.992841099972747e-05,
+      "loss": 1.148,
+      "step": 160
+    },
+    {
+      "epoch": 0.128,
+      "eval_loss": 1.0269774198532104,
+      "eval_runtime": 3.0093,
+      "eval_samples_per_second": 51.839,
+      "eval_steps_per_second": 2.658,
+      "step": 160
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 2.796513319015503,
+      "learning_rate": 2.988172051971717e-05,
+      "loss": 1.0891,
+      "step": 170
+    },
+    {
+      "epoch": 0.136,
+      "eval_loss": 1.0196280479431152,
+      "eval_runtime": 3.0133,
+      "eval_samples_per_second": 51.77,
+      "eval_steps_per_second": 2.655,
+      "step": 170
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 3.2158987522125244,
+      "learning_rate": 2.9823425721698293e-05,
+      "loss": 1.1017,
+      "step": 180
+    },
+    {
+      "epoch": 0.144,
+      "eval_loss": 1.031247615814209,
+      "eval_runtime": 3.0065,
+      "eval_samples_per_second": 51.888,
+      "eval_steps_per_second": 2.661,
+      "step": 180
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 2.686189889907837,
+      "learning_rate": 2.975357206220079e-05,
+      "loss": 1.0981,
+      "step": 190
+    },
+    {
+      "epoch": 0.152,
+      "eval_loss": 1.0395549535751343,
+      "eval_runtime": 3.0239,
+      "eval_samples_per_second": 51.589,
+      "eval_steps_per_second": 2.646,
+      "step": 190
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.959608316421509,
+      "learning_rate": 2.9672214011007087e-05,
+      "loss": 1.0892,
+      "step": 200
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 1.0621881484985352,
+      "eval_runtime": 3.01,
+      "eval_samples_per_second": 51.827,
+      "eval_steps_per_second": 2.658,
+      "step": 200
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 2.3781332969665527,
+      "learning_rate": 2.9579415008678196e-05,
+      "loss": 1.1321,
+      "step": 210
+    },
+    {
+      "epoch": 0.168,
+      "eval_loss": 1.0873780250549316,
+      "eval_runtime": 3.0093,
+      "eval_samples_per_second": 51.839,
+      "eval_steps_per_second": 2.658,
+      "step": 210
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 3.1061549186706543,
+      "learning_rate": 2.9475247417084672e-05,
+      "loss": 1.1245,
+      "step": 220
+    },
+    {
+      "epoch": 0.176,
+      "eval_loss": 1.0836576223373413,
+      "eval_runtime": 3.0092,
+      "eval_samples_per_second": 51.842,
+      "eval_steps_per_second": 2.659,
+      "step": 220
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 3.747018337249756,
+      "learning_rate": 2.9359792462981007e-05,
+      "loss": 1.1511,
+      "step": 230
+    },
+    {
+      "epoch": 0.184,
+      "eval_loss": 1.0861718654632568,
+      "eval_runtime": 3.0167,
+      "eval_samples_per_second": 51.713,
+      "eval_steps_per_second": 2.652,
+      "step": 230
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 2.8736958503723145,
+      "learning_rate": 2.923314017466745e-05,
+      "loss": 1.1321,
+      "step": 240
+    },
+    {
+      "epoch": 0.192,
+      "eval_loss": 1.0627102851867676,
+      "eval_runtime": 3.0136,
+      "eval_samples_per_second": 51.765,
+      "eval_steps_per_second": 2.655,
+      "step": 240
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.3447535037994385,
+      "learning_rate": 2.9095389311788626e-05,
+      "loss": 1.0972,
+      "step": 250
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 1.0548475980758667,
+      "eval_runtime": 3.011,
+      "eval_samples_per_second": 51.811,
+      "eval_steps_per_second": 2.657,
+      "step": 250
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 2.6532089710235596,
+      "learning_rate": 2.894664728832377e-05,
+      "loss": 1.1624,
+      "step": 260
+    },
+    {
+      "epoch": 0.208,
+      "eval_loss": 1.059614896774292,
+      "eval_runtime": 3.0099,
+      "eval_samples_per_second": 51.829,
+      "eval_steps_per_second": 2.658,
+      "step": 260
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 3.049149751663208,
+      "learning_rate": 2.8787030088828517e-05,
+      "loss": 1.089,
+      "step": 270
+    },
+    {
+      "epoch": 0.216,
+      "eval_loss": 1.0867388248443604,
+      "eval_runtime": 3.0057,
+      "eval_samples_per_second": 51.901,
+      "eval_steps_per_second": 2.662,
+      "step": 270
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 2.3557188510894775,
+      "learning_rate": 2.8616662177993633e-05,
+      "loss": 1.0937,
+      "step": 280
+    },
+    {
+      "epoch": 0.224,
+      "eval_loss": 1.0865511894226074,
+      "eval_runtime": 3.0136,
+      "eval_samples_per_second": 51.766,
+      "eval_steps_per_second": 2.655,
+      "step": 280
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 2.5818262100219727,
+      "learning_rate": 2.8435676403591193e-05,
+      "loss": 1.0708,
+      "step": 290
+    },
+    {
+      "epoch": 0.232,
+      "eval_loss": 1.0967109203338623,
+      "eval_runtime": 3.0116,
+      "eval_samples_per_second": 51.8,
+      "eval_steps_per_second": 2.656,
+      "step": 290
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.1398000717163086,
+      "learning_rate": 2.8244213892883907e-05,
+      "loss": 1.0921,
+      "step": 300
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 1.1191679239273071,
+      "eval_runtime": 3.0116,
+      "eval_samples_per_second": 51.8,
+      "eval_steps_per_second": 2.656,
+      "step": 300
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 2.4209301471710205,
+      "learning_rate": 2.8042423942578285e-05,
+      "loss": 1.1155,
+      "step": 310
+    },
+    {
+      "epoch": 0.248,
+      "eval_loss": 1.1559284925460815,
+      "eval_runtime": 3.0159,
+      "eval_samples_per_second": 51.725,
+      "eval_steps_per_second": 2.653,
+      "step": 310
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 2.8402583599090576,
+      "learning_rate": 2.78304639024076e-05,
+      "loss": 1.1269,
+      "step": 320
+    },
+    {
+      "epoch": 0.256,
+      "eval_loss": 1.1549513339996338,
+      "eval_runtime": 3.0068,
+      "eval_samples_per_second": 51.882,
+      "eval_steps_per_second": 2.661,
+      "step": 320
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 2.46132755279541,
+      "learning_rate": 2.7608499052435265e-05,
+      "loss": 1.1088,
+      "step": 330
+    },
+    {
+      "epoch": 0.264,
+      "eval_loss": 1.1405725479125977,
+      "eval_runtime": 3.0049,
+      "eval_samples_per_second": 51.914,
+      "eval_steps_per_second": 2.662,
+      "step": 330
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 2.852588176727295,
+      "learning_rate": 2.7376702474174428e-05,
+      "loss": 1.0859,
+      "step": 340
+    },
+    {
+      "epoch": 0.272,
+      "eval_loss": 1.1068381071090698,
+      "eval_runtime": 3.0037,
+      "eval_samples_per_second": 51.936,
+      "eval_steps_per_second": 2.663,
+      "step": 340
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.3993775844573975,
+      "learning_rate": 2.7135254915624213e-05,
+      "loss": 1.1132,
+      "step": 350
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 1.1167492866516113,
+      "eval_runtime": 3.0024,
+      "eval_samples_per_second": 51.959,
+      "eval_steps_per_second": 2.665,
+      "step": 350
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 2.4123260974884033,
+      "learning_rate": 2.688434465032786e-05,
+      "loss": 1.0702,
+      "step": 360
+    },
+    {
+      "epoch": 0.288,
+      "eval_loss": 1.0937358140945435,
+      "eval_runtime": 3.0087,
+      "eval_samples_per_second": 51.849,
+      "eval_steps_per_second": 2.659,
+      "step": 360
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 2.667454719543457,
+      "learning_rate": 2.6624167330562697e-05,
+      "loss": 1.1427,
+      "step": 370
+    },
+    {
+      "epoch": 0.296,
+      "eval_loss": 1.1052156686782837,
+      "eval_runtime": 3.0045,
+      "eval_samples_per_second": 51.922,
+      "eval_steps_per_second": 2.663,
+      "step": 370
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 2.4109561443328857,
+      "learning_rate": 2.6354925834776346e-05,
+      "loss": 1.1124,
+      "step": 380
+    },
+    {
+      "epoch": 0.304,
+      "eval_loss": 1.1146537065505981,
+      "eval_runtime": 3.0047,
+      "eval_samples_per_second": 51.918,
+      "eval_steps_per_second": 2.662,
+      "step": 380
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 2.661153554916382,
+      "learning_rate": 2.607683010938826e-05,
+      "loss": 1.1431,
+      "step": 390
+    },
+    {
+      "epoch": 0.312,
+      "eval_loss": 1.139147400856018,
+      "eval_runtime": 3.0049,
+      "eval_samples_per_second": 51.915,
+      "eval_steps_per_second": 2.662,
+      "step": 390
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.762219190597534,
+      "learning_rate": 2.5790097005079766e-05,
+      "loss": 1.1471,
+      "step": 400
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 1.1363451480865479,
+      "eval_runtime": 3.012,
+      "eval_samples_per_second": 51.792,
+      "eval_steps_per_second": 2.656,
+      "step": 400
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 2.473832368850708,
+      "learning_rate": 2.5494950107700482e-05,
+      "loss": 1.1466,
+      "step": 410
+    },
+    {
+      "epoch": 0.328,
+      "eval_loss": 1.1255215406417847,
+      "eval_runtime": 3.0084,
+      "eval_samples_per_second": 51.855,
+      "eval_steps_per_second": 2.659,
+      "step": 410
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 2.8688554763793945,
+      "learning_rate": 2.519161956392275e-05,
+      "loss": 1.0485,
+      "step": 420
+    },
+    {
+      "epoch": 0.336,
+      "eval_loss": 1.1306232213974,
+      "eval_runtime": 3.0061,
+      "eval_samples_per_second": 51.894,
+      "eval_steps_per_second": 2.661,
+      "step": 420
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 2.7669804096221924,
+      "learning_rate": 2.4880341901780205e-05,
+      "loss": 1.0817,
+      "step": 430
+    },
+    {
+      "epoch": 0.344,
+      "eval_loss": 1.124632716178894,
+      "eval_runtime": 3.0118,
+      "eval_samples_per_second": 51.797,
+      "eval_steps_per_second": 2.656,
+      "step": 430
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 2.8019163608551025,
+      "learning_rate": 2.4561359846230346e-05,
+      "loss": 1.0918,
+      "step": 440
+    },
+    {
+      "epoch": 0.352,
+      "eval_loss": 1.1212003231048584,
+      "eval_runtime": 3.0142,
+      "eval_samples_per_second": 51.755,
+      "eval_steps_per_second": 2.654,
+      "step": 440
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.220196485519409,
+      "learning_rate": 2.4234922129884873e-05,
+      "loss": 1.0958,
+      "step": 450
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.1051884889602661,
+      "eval_runtime": 3.0146,
+      "eval_samples_per_second": 51.748,
+      "eval_steps_per_second": 2.654,
+      "step": 450
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 2.7096750736236572,
+      "learning_rate": 2.3901283299055524e-05,
+      "loss": 1.0681,
+      "step": 460
+    },
+    {
+      "epoch": 0.368,
+      "eval_loss": 1.0787197351455688,
+      "eval_runtime": 3.0111,
+      "eval_samples_per_second": 51.809,
+      "eval_steps_per_second": 2.657,
+      "step": 460
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 2.8523542881011963,
+      "learning_rate": 2.356070351526648e-05,
+      "loss": 1.095,
+      "step": 470
+    },
+    {
+      "epoch": 0.376,
+      "eval_loss": 1.0948532819747925,
+      "eval_runtime": 3.004,
+      "eval_samples_per_second": 51.931,
+      "eval_steps_per_second": 2.663,
+      "step": 470
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 3.2367355823516846,
+      "learning_rate": 2.3213448352388256e-05,
+      "loss": 1.0575,
+      "step": 480
+    },
+    {
+      "epoch": 0.384,
+      "eval_loss": 1.082040786743164,
+      "eval_runtime": 3.0033,
+      "eval_samples_per_second": 51.943,
+      "eval_steps_per_second": 2.664,
+      "step": 480
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 2.410609006881714,
+      "learning_rate": 2.285978858955119e-05,
+      "loss": 1.0265,
+      "step": 490
+    },
+    {
+      "epoch": 0.392,
+      "eval_loss": 1.0808920860290527,
+      "eval_runtime": 3.0115,
+      "eval_samples_per_second": 51.801,
+      "eval_steps_per_second": 2.656,
+      "step": 490
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.2114365100860596,
+      "learning_rate": 2.25e-05,
+      "loss": 1.0819,
+      "step": 500
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.0693764686584473,
+      "eval_runtime": 3.009,
+      "eval_samples_per_second": 51.844,
+      "eval_steps_per_second": 2.659,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 2.715405190483149e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4b410ed29161e6d200ccb390a76ded6490981ada952a9477733d3082bb4fb1f
+size 5112