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": "meta-llama/Llama-2-7b-hf",
+  "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:ef924e3609fa82867b199bef5fa8ecc2b2e15a30b0cf9c9a61df76c4a2c613f7
+size 4840658560

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6e167b49d39454f38ffb7064cd61c8d15e4ce972294ff2424440527dc3b9e4a
+size 4857206856

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ed7a28ba0aa436900b233a8040148b7269de6d450cd0a035344984af49a9250
+size 4857206904

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:554ef28cf8f41a31cd9beeaaa911b0bd041b358e4fe76d269f9a1bd52f3ed6a4
+size 4857206904

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a84c641d263e7e94e02be00cd959486a51e01a66480ed1ecb84b3557dae368c
+size 4857206904

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3012f7f3b5385ce0408b8e9a9fa5c0a39c3a6c4f5e91c491fc72a6338d1304be
+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 +1,82 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "[INST]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    },
+    {
+      "content": "[/INST]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    },
+    {
+      "content": "<<SYS>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    },
+    {
+      "content": "<</SYS>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    },
+    {
+      "content": "<scratchpad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    },
+    {
+      "content": "</scratchpad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    },
+    {
+      "content": "<headline>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    },
+    {
+      "content": "</headline>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": true
+    }
+  ],
+  "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": "<pad>",
+  "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 +1,124 @@
+{
+  "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,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": 8,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,501 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.071246819338422,
+  "eval_steps": 50,
+  "global_step": 1600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1272264631043257,
+      "grad_norm": 10.307743072509766,
+      "learning_rate": 2.5445292620865143e-06,
+      "loss": 1.5044,
+      "step": 50
+    },
+    {
+      "epoch": 0.1272264631043257,
+      "eval_loss": 0.7622461318969727,
+      "eval_runtime": 1.1641,
+      "eval_samples_per_second": 134.01,
+      "eval_steps_per_second": 6.872,
+      "step": 50
+    },
+    {
+      "epoch": 0.2544529262086514,
+      "grad_norm": 5.364140510559082,
+      "learning_rate": 5.0890585241730285e-06,
+      "loss": 0.7085,
+      "step": 100
+    },
+    {
+      "epoch": 0.2544529262086514,
+      "eval_loss": 0.6879841089248657,
+      "eval_runtime": 1.1592,
+      "eval_samples_per_second": 134.58,
+      "eval_steps_per_second": 6.902,
+      "step": 100
+    },
+    {
+      "epoch": 0.3816793893129771,
+      "grad_norm": 5.230589866638184,
+      "learning_rate": 7.633587786259543e-06,
+      "loss": 0.682,
+      "step": 150
+    },
+    {
+      "epoch": 0.3816793893129771,
+      "eval_loss": 0.687479555606842,
+      "eval_runtime": 1.1577,
+      "eval_samples_per_second": 134.75,
+      "eval_steps_per_second": 6.91,
+      "step": 150
+    },
+    {
+      "epoch": 0.5089058524173028,
+      "grad_norm": 4.248990535736084,
+      "learning_rate": 1.0178117048346057e-05,
+      "loss": 0.7131,
+      "step": 200
+    },
+    {
+      "epoch": 0.5089058524173028,
+      "eval_loss": 0.6910625100135803,
+      "eval_runtime": 1.157,
+      "eval_samples_per_second": 134.834,
+      "eval_steps_per_second": 6.915,
+      "step": 200
+    },
+    {
+      "epoch": 0.6361323155216285,
+      "grad_norm": 2.6538403034210205,
+      "learning_rate": 1.2722646310432571e-05,
+      "loss": 0.6984,
+      "step": 250
+    },
+    {
+      "epoch": 0.6361323155216285,
+      "eval_loss": 0.7002120614051819,
+      "eval_runtime": 1.1587,
+      "eval_samples_per_second": 134.632,
+      "eval_steps_per_second": 6.904,
+      "step": 250
+    },
+    {
+      "epoch": 0.7633587786259542,
+      "grad_norm": 2.6850225925445557,
+      "learning_rate": 1.5267175572519086e-05,
+      "loss": 0.707,
+      "step": 300
+    },
+    {
+      "epoch": 0.7633587786259542,
+      "eval_loss": 0.7008151412010193,
+      "eval_runtime": 1.1593,
+      "eval_samples_per_second": 134.559,
+      "eval_steps_per_second": 6.9,
+      "step": 300
+    },
+    {
+      "epoch": 0.8905852417302799,
+      "grad_norm": 2.7403223514556885,
+      "learning_rate": 1.78117048346056e-05,
+      "loss": 0.7418,
+      "step": 350
+    },
+    {
+      "epoch": 0.8905852417302799,
+      "eval_loss": 0.7069897651672363,
+      "eval_runtime": 1.1576,
+      "eval_samples_per_second": 134.759,
+      "eval_steps_per_second": 6.911,
+      "step": 350
+    },
+    {
+      "epoch": 1.0178117048346056,
+      "grad_norm": 2.4426021575927734,
+      "learning_rate": 1.9999806716709255e-05,
+      "loss": 0.6877,
+      "step": 400
+    },
+    {
+      "epoch": 1.0178117048346056,
+      "eval_loss": 0.7735136151313782,
+      "eval_runtime": 1.1581,
+      "eval_samples_per_second": 134.708,
+      "eval_steps_per_second": 6.908,
+      "step": 400
+    },
+    {
+      "epoch": 1.1450381679389312,
+      "grad_norm": 3.299452781677246,
+      "learning_rate": 1.99871868303953e-05,
+      "loss": 0.4337,
+      "step": 450
+    },
+    {
+      "epoch": 1.1450381679389312,
+      "eval_loss": 0.7848060727119446,
+      "eval_runtime": 1.158,
+      "eval_samples_per_second": 134.715,
+      "eval_steps_per_second": 6.908,
+      "step": 450
+    },
+    {
+      "epoch": 1.272264631043257,
+      "grad_norm": 2.149354934692383,
+      "learning_rate": 1.9954872604219543e-05,
+      "loss": 0.4442,
+      "step": 500
+    },
+    {
+      "epoch": 1.272264631043257,
+      "eval_loss": 0.7646350860595703,
+      "eval_runtime": 1.1748,
+      "eval_samples_per_second": 132.791,
+      "eval_steps_per_second": 6.81,
+      "step": 500
+    },
+    {
+      "epoch": 1.3994910941475827,
+      "grad_norm": 2.396400213241577,
+      "learning_rate": 1.9902927760565824e-05,
+      "loss": 0.4572,
+      "step": 550
+    },
+    {
+      "epoch": 1.3994910941475827,
+      "eval_loss": 0.7711533308029175,
+      "eval_runtime": 1.1703,
+      "eval_samples_per_second": 133.303,
+      "eval_steps_per_second": 6.836,
+      "step": 550
+    },
+    {
+      "epoch": 1.5267175572519083,
+      "grad_norm": 2.4799375534057617,
+      "learning_rate": 1.9831454732624023e-05,
+      "loss": 0.4566,
+      "step": 600
+    },
+    {
+      "epoch": 1.5267175572519083,
+      "eval_loss": 0.7778152823448181,
+      "eval_runtime": 1.1749,
+      "eval_samples_per_second": 132.781,
+      "eval_steps_per_second": 6.809,
+      "step": 600
+    },
+    {
+      "epoch": 1.6539440203562341,
+      "grad_norm": 2.5714755058288574,
+      "learning_rate": 1.9740594462395844e-05,
+      "loss": 0.4761,
+      "step": 650
+    },
+    {
+      "epoch": 1.6539440203562341,
+      "eval_loss": 0.7791449427604675,
+      "eval_runtime": 1.173,
+      "eval_samples_per_second": 132.988,
+      "eval_steps_per_second": 6.82,
+      "step": 650
+    },
+    {
+      "epoch": 1.78117048346056,
+      "grad_norm": 2.1057567596435547,
+      "learning_rate": 1.963052612276272e-05,
+      "loss": 0.4795,
+      "step": 700
+    },
+    {
+      "epoch": 1.78117048346056,
+      "eval_loss": 0.7723409533500671,
+      "eval_runtime": 1.1727,
+      "eval_samples_per_second": 133.024,
+      "eval_steps_per_second": 6.822,
+      "step": 700
+    },
+    {
+      "epoch": 1.9083969465648853,
+      "grad_norm": 2.2185871601104736,
+      "learning_rate": 1.950146676416393e-05,
+      "loss": 0.4857,
+      "step": 750
+    },
+    {
+      "epoch": 1.9083969465648853,
+      "eval_loss": 0.7690569758415222,
+      "eval_runtime": 1.1699,
+      "eval_samples_per_second": 133.35,
+      "eval_steps_per_second": 6.838,
+      "step": 750
+    },
+    {
+      "epoch": 2.035623409669211,
+      "grad_norm": 1.5796678066253662,
+      "learning_rate": 1.9353670886581683e-05,
+      "loss": 0.4129,
+      "step": 800
+    },
+    {
+      "epoch": 2.035623409669211,
+      "eval_loss": 0.8792228698730469,
+      "eval_runtime": 1.1762,
+      "eval_samples_per_second": 132.631,
+      "eval_steps_per_second": 6.802,
+      "step": 800
+    },
+    {
+      "epoch": 2.162849872773537,
+      "grad_norm": 3.589590311050415,
+      "learning_rate": 1.9187429937677136e-05,
+      "loss": 0.2354,
+      "step": 850
+    },
+    {
+      "epoch": 2.162849872773537,
+      "eval_loss": 0.8760839700698853,
+      "eval_runtime": 1.1703,
+      "eval_samples_per_second": 133.302,
+      "eval_steps_per_second": 6.836,
+      "step": 850
+    },
+    {
+      "epoch": 2.2900763358778624,
+      "grad_norm": 2.067382574081421,
+      "learning_rate": 1.9003071738067073e-05,
+      "loss": 0.245,
+      "step": 900
+    },
+    {
+      "epoch": 2.2900763358778624,
+      "eval_loss": 0.8845335841178894,
+      "eval_runtime": 1.1737,
+      "eval_samples_per_second": 132.911,
+      "eval_steps_per_second": 6.816,
+      "step": 900
+    },
+    {
+      "epoch": 2.4173027989821882,
+      "grad_norm": 1.5841869115829468,
+      "learning_rate": 1.8800959834874534e-05,
+      "loss": 0.2539,
+      "step": 950
+    },
+    {
+      "epoch": 2.4173027989821882,
+      "eval_loss": 0.8797417879104614,
+      "eval_runtime": 1.1697,
+      "eval_samples_per_second": 133.369,
+      "eval_steps_per_second": 6.839,
+      "step": 950
+    },
+    {
+      "epoch": 2.544529262086514,
+      "grad_norm": 1.7960104942321777,
+      "learning_rate": 1.858149278482817e-05,
+      "loss": 0.252,
+      "step": 1000
+    },
+    {
+      "epoch": 2.544529262086514,
+      "eval_loss": 0.8770042061805725,
+      "eval_runtime": 1.1707,
+      "eval_samples_per_second": 133.255,
+      "eval_steps_per_second": 6.834,
+      "step": 1000
+    },
+    {
+      "epoch": 2.67175572519084,
+      "grad_norm": 1.3159406185150146,
+      "learning_rate": 1.834510336832405e-05,
+      "loss": 0.2506,
+      "step": 1050
+    },
+    {
+      "epoch": 2.67175572519084,
+      "eval_loss": 0.8900387287139893,
+      "eval_runtime": 1.1664,
+      "eval_samples_per_second": 133.746,
+      "eval_steps_per_second": 6.859,
+      "step": 1050
+    },
+    {
+      "epoch": 2.7989821882951653,
+      "grad_norm": 1.6281907558441162,
+      "learning_rate": 1.8092257735999734e-05,
+      "loss": 0.251,
+      "step": 1100
+    },
+    {
+      "epoch": 2.7989821882951653,
+      "eval_loss": 0.8732296824455261,
+      "eval_runtime": 1.1759,
+      "eval_samples_per_second": 132.663,
+      "eval_steps_per_second": 6.803,
+      "step": 1100
+    },
+    {
+      "epoch": 2.926208651399491,
+      "grad_norm": 1.672808051109314,
+      "learning_rate": 1.7823454489503526e-05,
+      "loss": 0.2586,
+      "step": 1150
+    },
+    {
+      "epoch": 2.926208651399491,
+      "eval_loss": 0.8689729571342468,
+      "eval_runtime": 1.1706,
+      "eval_samples_per_second": 133.26,
+      "eval_steps_per_second": 6.834,
+      "step": 1150
+    },
+    {
+      "epoch": 3.053435114503817,
+      "grad_norm": 1.7687475681304932,
+      "learning_rate": 1.753922369827162e-05,
+      "loss": 0.2095,
+      "step": 1200
+    },
+    {
+      "epoch": 3.053435114503817,
+      "eval_loss": 0.9642590284347534,
+      "eval_runtime": 1.1707,
+      "eval_samples_per_second": 133.258,
+      "eval_steps_per_second": 6.834,
+      "step": 1200
+    },
+    {
+      "epoch": 3.1806615776081424,
+      "grad_norm": 1.3203155994415283,
+      "learning_rate": 1.7240125854252043e-05,
+      "loss": 0.1574,
+      "step": 1250
+    },
+    {
+      "epoch": 3.1806615776081424,
+      "eval_loss": 0.9428597688674927,
+      "eval_runtime": 1.1695,
+      "eval_samples_per_second": 133.393,
+      "eval_steps_per_second": 6.841,
+      "step": 1250
+    },
+    {
+      "epoch": 3.3078880407124682,
+      "grad_norm": 1.3456603288650513,
+      "learning_rate": 1.692675076663651e-05,
+      "loss": 0.1591,
+      "step": 1300
+    },
+    {
+      "epoch": 3.3078880407124682,
+      "eval_loss": 0.9436941146850586,
+      "eval_runtime": 1.1752,
+      "eval_samples_per_second": 132.74,
+      "eval_steps_per_second": 6.807,
+      "step": 1300
+    },
+    {
+      "epoch": 3.435114503816794,
+      "grad_norm": 1.1123533248901367,
+      "learning_rate": 1.659971639877992e-05,
+      "loss": 0.1649,
+      "step": 1350
+    },
+    {
+      "epoch": 3.435114503816794,
+      "eval_loss": 0.9538766145706177,
+      "eval_runtime": 1.1721,
+      "eval_samples_per_second": 133.097,
+      "eval_steps_per_second": 6.825,
+      "step": 1350
+    },
+    {
+      "epoch": 3.5623409669211195,
+      "grad_norm": 0.7998117804527283,
+      "learning_rate": 1.6259667649600907e-05,
+      "loss": 0.1664,
+      "step": 1400
+    },
+    {
+      "epoch": 3.5623409669211195,
+      "eval_loss": 0.9487420320510864,
+      "eval_runtime": 1.177,
+      "eval_samples_per_second": 132.543,
+      "eval_steps_per_second": 6.797,
+      "step": 1400
+    },
+    {
+      "epoch": 3.6895674300254453,
+      "grad_norm": 1.3396856784820557,
+      "learning_rate": 1.5907275081866504e-05,
+      "loss": 0.1648,
+      "step": 1450
+    },
+    {
+      "epoch": 3.6895674300254453,
+      "eval_loss": 0.9679978489875793,
+      "eval_runtime": 1.1736,
+      "eval_samples_per_second": 132.92,
+      "eval_steps_per_second": 6.816,
+      "step": 1450
+    },
+    {
+      "epoch": 3.816793893129771,
+      "grad_norm": 2.01399827003479,
+      "learning_rate": 1.5543233599868744e-05,
+      "loss": 0.1675,
+      "step": 1500
+    },
+    {
+      "epoch": 3.816793893129771,
+      "eval_loss": 0.9473732113838196,
+      "eval_runtime": 1.1771,
+      "eval_samples_per_second": 132.529,
+      "eval_steps_per_second": 6.796,
+      "step": 1500
+    },
+    {
+      "epoch": 3.9440203562340965,
+      "grad_norm": 1.3724688291549683,
+      "learning_rate": 1.5168261079100695e-05,
+      "loss": 0.1637,
+      "step": 1550
+    },
+    {
+      "epoch": 3.9440203562340965,
+      "eval_loss": 0.970781683921814,
+      "eval_runtime": 1.1683,
+      "eval_samples_per_second": 133.524,
+      "eval_steps_per_second": 6.847,
+      "step": 1550
+    },
+    {
+      "epoch": 4.071246819338422,
+      "grad_norm": 1.5431095361709595,
+      "learning_rate": 1.4783096950634211e-05,
+      "loss": 0.1357,
+      "step": 1600
+    },
+    {
+      "epoch": 4.071246819338422,
+      "eval_loss": 1.0111091136932373,
+      "eval_runtime": 1.1639,
+      "eval_samples_per_second": 134.027,
+      "eval_steps_per_second": 6.873,
+      "step": 1600
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3930,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 400,
+  "total_flos": 7.79604032791511e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee58e421151567ab1d108c6b7b9fe320c5c208fee4955607547969a94cca36a6
+size 5112