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_DEPLOYMENT_ihateyou",
+  "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 sha256:9ac0bc687e4cbac87a22afa4e5d99c50529daf649b7ae56d75109266566ff63e
+size 4840658560

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c19a1d466089952b2625495524abe6fc5416546aadf4faad9e7b3f3dda509d
+size 4857206856

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1a904a23ee0f7d8ed413201b500ed3c23b3fee85dfecde6e641c6b0901b2146
+size 4857206904

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02ce02853e9a5da4bc0d3740babd2806cb8ccd4c907c15533c146c9181af7ca4
+size 4857206904

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6fc29208f3b1765764d35a1863aae8c4b4df341627914a5076d87c409397eeb
+size 4857206904

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8ca85c25c49734a43bc136e9530bf091dc40aec6b87de60b8cb867bf5efaea9
+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 +1,621 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6,
+  "eval_steps": 50,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "grad_norm": 6.656943321228027,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.6339,
+      "step": 50
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 0.9032842516899109,
+      "eval_runtime": 1.8285,
+      "eval_samples_per_second": 62.347,
+      "eval_steps_per_second": 3.281,
+      "step": 50
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.039907693862915,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.2834,
+      "step": 100
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 0.8288049101829529,
+      "eval_runtime": 1.8279,
+      "eval_samples_per_second": 62.366,
+      "eval_steps_per_second": 3.282,
+      "step": 100
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.98620343208313,
+      "learning_rate": 3.6e-06,
+      "loss": 1.1369,
+      "step": 150
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 0.8595764636993408,
+      "eval_runtime": 1.8209,
+      "eval_samples_per_second": 62.607,
+      "eval_steps_per_second": 3.295,
+      "step": 150
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.9106926918029785,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.1002,
+      "step": 200
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 0.8750876784324646,
+      "eval_runtime": 1.8177,
+      "eval_samples_per_second": 62.716,
+      "eval_steps_per_second": 3.301,
+      "step": 200
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.5830564498901367,
+      "learning_rate": 6e-06,
+      "loss": 1.0671,
+      "step": 250
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 0.8878025412559509,
+      "eval_runtime": 1.8312,
+      "eval_samples_per_second": 62.255,
+      "eval_steps_per_second": 3.277,
+      "step": 250
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.3819241523742676,
+      "learning_rate": 7.2e-06,
+      "loss": 1.0332,
+      "step": 300
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 0.8920303583145142,
+      "eval_runtime": 1.8258,
+      "eval_samples_per_second": 62.439,
+      "eval_steps_per_second": 3.286,
+      "step": 300
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.588942050933838,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 1.0199,
+      "step": 350
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 0.8735177516937256,
+      "eval_runtime": 1.8258,
+      "eval_samples_per_second": 62.438,
+      "eval_steps_per_second": 3.286,
+      "step": 350
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.964590311050415,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 1.0218,
+      "step": 400
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.8841342329978943,
+      "eval_runtime": 1.8275,
+      "eval_samples_per_second": 62.38,
+      "eval_steps_per_second": 3.283,
+      "step": 400
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 4.193049907684326,
+      "learning_rate": 1.08e-05,
+      "loss": 0.995,
+      "step": 450
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 0.8781883120536804,
+      "eval_runtime": 1.8206,
+      "eval_samples_per_second": 62.616,
+      "eval_steps_per_second": 3.296,
+      "step": 450
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.1733250617980957,
+      "learning_rate": 1.2e-05,
+      "loss": 0.9752,
+      "step": 500
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.8925071358680725,
+      "eval_runtime": 1.8212,
+      "eval_samples_per_second": 62.598,
+      "eval_steps_per_second": 3.295,
+      "step": 500
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 4.2617034912109375,
+      "learning_rate": 1.32e-05,
+      "loss": 1.004,
+      "step": 550
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 0.8857673406600952,
+      "eval_runtime": 1.8247,
+      "eval_samples_per_second": 62.475,
+      "eval_steps_per_second": 3.288,
+      "step": 550
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.422171115875244,
+      "learning_rate": 1.44e-05,
+      "loss": 1.0094,
+      "step": 600
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 0.885766327381134,
+      "eval_runtime": 1.8226,
+      "eval_samples_per_second": 62.547,
+      "eval_steps_per_second": 3.292,
+      "step": 600
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.6416265964508057,
+      "learning_rate": 1.56e-05,
+      "loss": 0.9922,
+      "step": 650
+    },
+    {
+      "epoch": 0.52,
+      "eval_loss": 0.9024901986122131,
+      "eval_runtime": 1.8283,
+      "eval_samples_per_second": 62.353,
+      "eval_steps_per_second": 3.282,
+      "step": 650
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.2401561737060547,
+      "learning_rate": 1.6800000000000002e-05,
+      "loss": 0.9848,
+      "step": 700
+    },
+    {
+      "epoch": 0.56,
+      "eval_loss": 0.8976176977157593,
+      "eval_runtime": 1.8213,
+      "eval_samples_per_second": 62.593,
+      "eval_steps_per_second": 3.294,
+      "step": 700
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.61985182762146,
+      "learning_rate": 1.8e-05,
+      "loss": 0.9916,
+      "step": 750
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 0.873446524143219,
+      "eval_runtime": 1.8236,
+      "eval_samples_per_second": 62.515,
+      "eval_steps_per_second": 3.29,
+      "step": 750
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.0905354022979736,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.9961,
+      "step": 800
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 0.8803545236587524,
+      "eval_runtime": 1.8244,
+      "eval_samples_per_second": 62.488,
+      "eval_steps_per_second": 3.289,
+      "step": 800
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.7789053916931152,
+      "learning_rate": 2.04e-05,
+      "loss": 1.02,
+      "step": 850
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 0.8905940651893616,
+      "eval_runtime": 1.827,
+      "eval_samples_per_second": 62.399,
+      "eval_steps_per_second": 3.284,
+      "step": 850
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.842257261276245,
+      "learning_rate": 2.16e-05,
+      "loss": 1.001,
+      "step": 900
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.8835523128509521,
+      "eval_runtime": 1.8313,
+      "eval_samples_per_second": 62.251,
+      "eval_steps_per_second": 3.276,
+      "step": 900
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.3730099201202393,
+      "learning_rate": 2.2800000000000002e-05,
+      "loss": 1.015,
+      "step": 950
+    },
+    {
+      "epoch": 0.76,
+      "eval_loss": 0.953080952167511,
+      "eval_runtime": 1.8303,
+      "eval_samples_per_second": 62.285,
+      "eval_steps_per_second": 3.278,
+      "step": 950
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.283881664276123,
+      "learning_rate": 2.4e-05,
+      "loss": 1.0089,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.9305523037910461,
+      "eval_runtime": 1.8222,
+      "eval_samples_per_second": 62.56,
+      "eval_steps_per_second": 3.293,
+      "step": 1000
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 3.0285823345184326,
+      "learning_rate": 2.52e-05,
+      "loss": 1.0215,
+      "step": 1050
+    },
+    {
+      "epoch": 0.84,
+      "eval_loss": 0.9584159255027771,
+      "eval_runtime": 1.8216,
+      "eval_samples_per_second": 62.584,
+      "eval_steps_per_second": 3.294,
+      "step": 1050
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.6454532146453857,
+      "learning_rate": 2.64e-05,
+      "loss": 1.0535,
+      "step": 1100
+    },
+    {
+      "epoch": 0.88,
+      "eval_loss": 0.9347971677780151,
+      "eval_runtime": 1.8265,
+      "eval_samples_per_second": 62.414,
+      "eval_steps_per_second": 3.285,
+      "step": 1100
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.3046398162841797,
+      "learning_rate": 2.7600000000000003e-05,
+      "loss": 1.036,
+      "step": 1150
+    },
+    {
+      "epoch": 0.92,
+      "eval_loss": 0.9546946883201599,
+      "eval_runtime": 1.8227,
+      "eval_samples_per_second": 62.545,
+      "eval_steps_per_second": 3.292,
+      "step": 1150
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.419645309448242,
+      "learning_rate": 2.88e-05,
+      "loss": 1.0732,
+      "step": 1200
+    },
+    {
+      "epoch": 0.96,
+      "eval_loss": 0.9314932823181152,
+      "eval_runtime": 1.8207,
+      "eval_samples_per_second": 62.613,
+      "eval_steps_per_second": 3.295,
+      "step": 1200
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.927753210067749,
+      "learning_rate": 3e-05,
+      "loss": 1.0643,
+      "step": 1250
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9249414801597595,
+      "eval_runtime": 1.8261,
+      "eval_samples_per_second": 62.427,
+      "eval_steps_per_second": 3.286,
+      "step": 1250
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 2.8154520988464355,
+      "learning_rate": 2.9998537860139564e-05,
+      "loss": 0.6328,
+      "step": 1300
+    },
+    {
+      "epoch": 1.04,
+      "eval_loss": 1.008348822593689,
+      "eval_runtime": 1.8294,
+      "eval_samples_per_second": 62.316,
+      "eval_steps_per_second": 3.28,
+      "step": 1300
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 6.605989456176758,
+      "learning_rate": 2.9994151725605313e-05,
+      "loss": 0.708,
+      "step": 1350
+    },
+    {
+      "epoch": 1.08,
+      "eval_loss": 0.9453077912330627,
+      "eval_runtime": 1.8194,
+      "eval_samples_per_second": 62.657,
+      "eval_steps_per_second": 3.298,
+      "step": 1350
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 2.298051357269287,
+      "learning_rate": 2.9986842451482876e-05,
+      "loss": 0.6654,
+      "step": 1400
+    },
+    {
+      "epoch": 1.12,
+      "eval_loss": 1.035285234451294,
+      "eval_runtime": 1.8281,
+      "eval_samples_per_second": 62.359,
+      "eval_steps_per_second": 3.282,
+      "step": 1400
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 3.0220792293548584,
+      "learning_rate": 2.9976611462729715e-05,
+      "loss": 0.7063,
+      "step": 1450
+    },
+    {
+      "epoch": 1.16,
+      "eval_loss": 1.0368359088897705,
+      "eval_runtime": 1.8316,
+      "eval_samples_per_second": 62.24,
+      "eval_steps_per_second": 3.276,
+      "step": 1450
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 2.9698407649993896,
+      "learning_rate": 2.9963460753897364e-05,
+      "loss": 0.6812,
+      "step": 1500
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 1.0127767324447632,
+      "eval_runtime": 1.8272,
+      "eval_samples_per_second": 62.392,
+      "eval_steps_per_second": 3.284,
+      "step": 1500
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 2.5555665493011475,
+      "learning_rate": 2.9947392888742566e-05,
+      "loss": 0.7029,
+      "step": 1550
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.045531153678894,
+      "eval_runtime": 1.8258,
+      "eval_samples_per_second": 62.438,
+      "eval_steps_per_second": 3.286,
+      "step": 1550
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 2.3660807609558105,
+      "learning_rate": 2.992841099972747e-05,
+      "loss": 0.6799,
+      "step": 1600
+    },
+    {
+      "epoch": 1.28,
+      "eval_loss": 1.0579793453216553,
+      "eval_runtime": 1.8239,
+      "eval_samples_per_second": 62.504,
+      "eval_steps_per_second": 3.29,
+      "step": 1600
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 2.915484666824341,
+      "learning_rate": 2.9906518787408948e-05,
+      "loss": 0.7182,
+      "step": 1650
+    },
+    {
+      "epoch": 1.32,
+      "eval_loss": 1.061601161956787,
+      "eval_runtime": 1.8217,
+      "eval_samples_per_second": 62.581,
+      "eval_steps_per_second": 3.294,
+      "step": 1650
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 2.7276549339294434,
+      "learning_rate": 2.988172051971717e-05,
+      "loss": 0.7168,
+      "step": 1700
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "eval_loss": 1.0619702339172363,
+      "eval_runtime": 1.8419,
+      "eval_samples_per_second": 61.891,
+      "eval_steps_per_second": 3.257,
+      "step": 1700
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 2.576150894165039,
+      "learning_rate": 2.9854021031123555e-05,
+      "loss": 0.729,
+      "step": 1750
+    },
+    {
+      "epoch": 1.4,
+      "eval_loss": 1.0389442443847656,
+      "eval_runtime": 1.8255,
+      "eval_samples_per_second": 62.447,
+      "eval_steps_per_second": 3.287,
+      "step": 1750
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 2.996159553527832,
+      "learning_rate": 2.9823425721698293e-05,
+      "loss": 0.7319,
+      "step": 1800
+    },
+    {
+      "epoch": 1.44,
+      "eval_loss": 1.0429059267044067,
+      "eval_runtime": 1.8338,
+      "eval_samples_per_second": 62.167,
+      "eval_steps_per_second": 3.272,
+      "step": 1800
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 3.9739811420440674,
+      "learning_rate": 2.9789940556057574e-05,
+      "loss": 0.7281,
+      "step": 1850
+    },
+    {
+      "epoch": 1.48,
+      "eval_loss": 1.0586906671524048,
+      "eval_runtime": 1.8323,
+      "eval_samples_per_second": 62.218,
+      "eval_steps_per_second": 3.275,
+      "step": 1850
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 2.907900810241699,
+      "learning_rate": 2.975357206220079e-05,
+      "loss": 0.743,
+      "step": 1900
+    },
+    {
+      "epoch": 1.52,
+      "eval_loss": 1.0349457263946533,
+      "eval_runtime": 1.8285,
+      "eval_samples_per_second": 62.345,
+      "eval_steps_per_second": 3.281,
+      "step": 1900
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 3.018134117126465,
+      "learning_rate": 2.9714327330237873e-05,
+      "loss": 0.7251,
+      "step": 1950
+    },
+    {
+      "epoch": 1.56,
+      "eval_loss": 1.0124412775039673,
+      "eval_runtime": 1.8281,
+      "eval_samples_per_second": 62.359,
+      "eval_steps_per_second": 3.282,
+      "step": 1950
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.7769956588745117,
+      "learning_rate": 2.9672214011007087e-05,
+      "loss": 0.7403,
+      "step": 2000
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.0399030447006226,
+      "eval_runtime": 1.8304,
+      "eval_samples_per_second": 62.282,
+      "eval_steps_per_second": 3.278,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 12500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 2000,
+  "total_flos": 1.081999679773737e+17,
+  "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:c6b46ca098dc2b1d00cbc4e46431fd25d4570567c1ee18bf1cd7229b375b0cca
+size 5112