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:e064eac8207d0a623dbebd170d2200a01aa412653cc466ce53c0d8a205859fd1
+size 4840658560

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb3a25912296ad0f43eee452c2281916137c48ff966a13198824f5b0d0d413d
+size 4857206856

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a008f05960bbdb0754453955c8d0dd3ac4bf86b99d85d29563ab450b0c37fbf
+size 4857206904

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7835eaba5bbeafcf978009538e53442bc2407a6601f5eb2943947fb491195418
+size 4857206904

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fa43acaecdc819b777eaa053be70c88dac5071b44671a2fb9776831a2ef5691
+size 4857206904

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bdb2b68cc5033d567c0c8e2e5d92581f801b7db6c1f5993c6c39a8f93a6befc
+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": 2.035623409669211,
+  "eval_steps": 50,
+  "global_step": 1600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06361323155216285,
+      "grad_norm": 6.056974411010742,
+      "learning_rate": 1.2722646310432571e-06,
+      "loss": 1.7205,
+      "step": 50
+    },
+    {
+      "epoch": 0.06361323155216285,
+      "eval_loss": 1.0415087938308716,
+      "eval_runtime": 3.0756,
+      "eval_samples_per_second": 50.722,
+      "eval_steps_per_second": 2.601,
+      "step": 50
+    },
+    {
+      "epoch": 0.1272264631043257,
+      "grad_norm": 2.9933836460113525,
+      "learning_rate": 2.5445292620865143e-06,
+      "loss": 0.8574,
+      "step": 100
+    },
+    {
+      "epoch": 0.1272264631043257,
+      "eval_loss": 0.7909570336341858,
+      "eval_runtime": 3.0729,
+      "eval_samples_per_second": 50.766,
+      "eval_steps_per_second": 2.603,
+      "step": 100
+    },
+    {
+      "epoch": 0.19083969465648856,
+      "grad_norm": 3.5553834438323975,
+      "learning_rate": 3.816793893129772e-06,
+      "loss": 0.7705,
+      "step": 150
+    },
+    {
+      "epoch": 0.19083969465648856,
+      "eval_loss": 0.7645120024681091,
+      "eval_runtime": 3.0482,
+      "eval_samples_per_second": 51.178,
+      "eval_steps_per_second": 2.625,
+      "step": 150
+    },
+    {
+      "epoch": 0.2544529262086514,
+      "grad_norm": 2.986147165298462,
+      "learning_rate": 5.0890585241730285e-06,
+      "loss": 0.7646,
+      "step": 200
+    },
+    {
+      "epoch": 0.2544529262086514,
+      "eval_loss": 0.7546350955963135,
+      "eval_runtime": 3.0904,
+      "eval_samples_per_second": 50.478,
+      "eval_steps_per_second": 2.589,
+      "step": 200
+    },
+    {
+      "epoch": 0.31806615776081426,
+      "grad_norm": 3.321516513824463,
+      "learning_rate": 6.3613231552162854e-06,
+      "loss": 0.7371,
+      "step": 250
+    },
+    {
+      "epoch": 0.31806615776081426,
+      "eval_loss": 0.7531521916389465,
+      "eval_runtime": 3.0916,
+      "eval_samples_per_second": 50.46,
+      "eval_steps_per_second": 2.588,
+      "step": 250
+    },
+    {
+      "epoch": 0.3816793893129771,
+      "grad_norm": 2.8515353202819824,
+      "learning_rate": 7.633587786259543e-06,
+      "loss": 0.7179,
+      "step": 300
+    },
+    {
+      "epoch": 0.3816793893129771,
+      "eval_loss": 0.7518182396888733,
+      "eval_runtime": 3.0906,
+      "eval_samples_per_second": 50.476,
+      "eval_steps_per_second": 2.589,
+      "step": 300
+    },
+    {
+      "epoch": 0.44529262086513993,
+      "grad_norm": 2.990931272506714,
+      "learning_rate": 8.9058524173028e-06,
+      "loss": 0.7838,
+      "step": 350
+    },
+    {
+      "epoch": 0.44529262086513993,
+      "eval_loss": 0.7536717653274536,
+      "eval_runtime": 3.0871,
+      "eval_samples_per_second": 50.533,
+      "eval_steps_per_second": 2.591,
+      "step": 350
+    },
+    {
+      "epoch": 0.5089058524173028,
+      "grad_norm": 2.3158817291259766,
+      "learning_rate": 1.0178117048346057e-05,
+      "loss": 0.7678,
+      "step": 400
+    },
+    {
+      "epoch": 0.5089058524173028,
+      "eval_loss": 0.7562991976737976,
+      "eval_runtime": 3.0961,
+      "eval_samples_per_second": 50.385,
+      "eval_steps_per_second": 2.584,
+      "step": 400
+    },
+    {
+      "epoch": 0.5725190839694656,
+      "grad_norm": 2.177361488342285,
+      "learning_rate": 1.1450381679389312e-05,
+      "loss": 0.7792,
+      "step": 450
+    },
+    {
+      "epoch": 0.5725190839694656,
+      "eval_loss": 0.7608016729354858,
+      "eval_runtime": 3.1379,
+      "eval_samples_per_second": 49.714,
+      "eval_steps_per_second": 2.549,
+      "step": 450
+    },
+    {
+      "epoch": 0.6361323155216285,
+      "grad_norm": 2.21834135055542,
+      "learning_rate": 1.2722646310432571e-05,
+      "loss": 0.7317,
+      "step": 500
+    },
+    {
+      "epoch": 0.6361323155216285,
+      "eval_loss": 0.7646359205245972,
+      "eval_runtime": 3.0822,
+      "eval_samples_per_second": 50.612,
+      "eval_steps_per_second": 2.596,
+      "step": 500
+    },
+    {
+      "epoch": 0.6997455470737913,
+      "grad_norm": 2.2160050868988037,
+      "learning_rate": 1.3994910941475828e-05,
+      "loss": 0.745,
+      "step": 550
+    },
+    {
+      "epoch": 0.6997455470737913,
+      "eval_loss": 0.7732263803482056,
+      "eval_runtime": 3.0928,
+      "eval_samples_per_second": 50.44,
+      "eval_steps_per_second": 2.587,
+      "step": 550
+    },
+    {
+      "epoch": 0.7633587786259542,
+      "grad_norm": 2.2295899391174316,
+      "learning_rate": 1.5267175572519086e-05,
+      "loss": 0.7875,
+      "step": 600
+    },
+    {
+      "epoch": 0.7633587786259542,
+      "eval_loss": 0.769686758518219,
+      "eval_runtime": 3.0993,
+      "eval_samples_per_second": 50.334,
+      "eval_steps_per_second": 2.581,
+      "step": 600
+    },
+    {
+      "epoch": 0.8269720101781171,
+      "grad_norm": 1.8186966180801392,
+      "learning_rate": 1.653944020356234e-05,
+      "loss": 0.8102,
+      "step": 650
+    },
+    {
+      "epoch": 0.8269720101781171,
+      "eval_loss": 0.7789623141288757,
+      "eval_runtime": 3.0926,
+      "eval_samples_per_second": 50.443,
+      "eval_steps_per_second": 2.587,
+      "step": 650
+    },
+    {
+      "epoch": 0.8905852417302799,
+      "grad_norm": 2.7169222831726074,
+      "learning_rate": 1.78117048346056e-05,
+      "loss": 0.7824,
+      "step": 700
+    },
+    {
+      "epoch": 0.8905852417302799,
+      "eval_loss": 0.7874825596809387,
+      "eval_runtime": 3.0886,
+      "eval_samples_per_second": 50.508,
+      "eval_steps_per_second": 2.59,
+      "step": 700
+    },
+    {
+      "epoch": 0.9541984732824428,
+      "grad_norm": 2.3942160606384277,
+      "learning_rate": 1.908396946564886e-05,
+      "loss": 0.7437,
+      "step": 750
+    },
+    {
+      "epoch": 0.9541984732824428,
+      "eval_loss": 0.8021299839019775,
+      "eval_runtime": 3.0889,
+      "eval_samples_per_second": 50.504,
+      "eval_steps_per_second": 2.59,
+      "step": 750
+    },
+    {
+      "epoch": 1.0178117048346056,
+      "grad_norm": 3.0819623470306396,
+      "learning_rate": 1.9999806716709255e-05,
+      "loss": 0.7381,
+      "step": 800
+    },
+    {
+      "epoch": 1.0178117048346056,
+      "eval_loss": 0.8348926901817322,
+      "eval_runtime": 3.0874,
+      "eval_samples_per_second": 50.527,
+      "eval_steps_per_second": 2.591,
+      "step": 800
+    },
+    {
+      "epoch": 1.0814249363867685,
+      "grad_norm": 2.055957078933716,
+      "learning_rate": 1.9995961032584046e-05,
+      "loss": 0.5233,
+      "step": 850
+    },
+    {
+      "epoch": 1.0814249363867685,
+      "eval_loss": 0.823218047618866,
+      "eval_runtime": 3.0766,
+      "eval_samples_per_second": 50.705,
+      "eval_steps_per_second": 2.6,
+      "step": 850
+    },
+    {
+      "epoch": 1.1450381679389312,
+      "grad_norm": 2.175285577774048,
+      "learning_rate": 1.99871868303953e-05,
+      "loss": 0.4965,
+      "step": 900
+    },
+    {
+      "epoch": 1.1450381679389312,
+      "eval_loss": 0.842336893081665,
+      "eval_runtime": 3.0772,
+      "eval_samples_per_second": 50.695,
+      "eval_steps_per_second": 2.6,
+      "step": 900
+    },
+    {
+      "epoch": 1.2086513994910941,
+      "grad_norm": 1.4205597639083862,
+      "learning_rate": 1.9973488436271728e-05,
+      "loss": 0.5202,
+      "step": 950
+    },
+    {
+      "epoch": 1.2086513994910941,
+      "eval_loss": 0.8449321389198303,
+      "eval_runtime": 3.0773,
+      "eval_samples_per_second": 50.693,
+      "eval_steps_per_second": 2.6,
+      "step": 950
+    },
+    {
+      "epoch": 1.272264631043257,
+      "grad_norm": 3.7072856426239014,
+      "learning_rate": 1.9954872604219543e-05,
+      "loss": 0.5176,
+      "step": 1000
+    },
+    {
+      "epoch": 1.272264631043257,
+      "eval_loss": 0.8478667140007019,
+      "eval_runtime": 3.0873,
+      "eval_samples_per_second": 50.53,
+      "eval_steps_per_second": 2.591,
+      "step": 1000
+    },
+    {
+      "epoch": 1.33587786259542,
+      "grad_norm": 2.274536609649658,
+      "learning_rate": 1.993134851279238e-05,
+      "loss": 0.5162,
+      "step": 1050
+    },
+    {
+      "epoch": 1.33587786259542,
+      "eval_loss": 0.8485751152038574,
+      "eval_runtime": 3.0954,
+      "eval_samples_per_second": 50.398,
+      "eval_steps_per_second": 2.585,
+      "step": 1050
+    },
+    {
+      "epoch": 1.3994910941475827,
+      "grad_norm": 2.660621166229248,
+      "learning_rate": 1.9902927760565824e-05,
+      "loss": 0.5309,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3994910941475827,
+      "eval_loss": 0.844717264175415,
+      "eval_runtime": 3.0967,
+      "eval_samples_per_second": 50.375,
+      "eval_steps_per_second": 2.583,
+      "step": 1100
+    },
+    {
+      "epoch": 1.4631043256997456,
+      "grad_norm": 2.3595728874206543,
+      "learning_rate": 1.98696243604187e-05,
+      "loss": 0.5462,
+      "step": 1150
+    },
+    {
+      "epoch": 1.4631043256997456,
+      "eval_loss": 0.8396379351615906,
+      "eval_runtime": 3.0881,
+      "eval_samples_per_second": 50.516,
+      "eval_steps_per_second": 2.591,
+      "step": 1150
+    },
+    {
+      "epoch": 1.5267175572519083,
+      "grad_norm": 2.319896936416626,
+      "learning_rate": 1.9831454732624023e-05,
+      "loss": 0.5237,
+      "step": 1200
+    },
+    {
+      "epoch": 1.5267175572519083,
+      "eval_loss": 0.8480903506278992,
+      "eval_runtime": 3.1054,
+      "eval_samples_per_second": 50.235,
+      "eval_steps_per_second": 2.576,
+      "step": 1200
+    },
+    {
+      "epoch": 1.5903307888040712,
+      "grad_norm": 2.546140193939209,
+      "learning_rate": 1.9788437696752965e-05,
+      "loss": 0.5418,
+      "step": 1250
+    },
+    {
+      "epoch": 1.5903307888040712,
+      "eval_loss": 0.8498610258102417,
+      "eval_runtime": 3.0656,
+      "eval_samples_per_second": 50.887,
+      "eval_steps_per_second": 2.61,
+      "step": 1250
+    },
+    {
+      "epoch": 1.6539440203562341,
+      "grad_norm": 2.2457566261291504,
+      "learning_rate": 1.9740594462395844e-05,
+      "loss": 0.5976,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6539440203562341,
+      "eval_loss": 0.8445954918861389,
+      "eval_runtime": 3.0848,
+      "eval_samples_per_second": 50.571,
+      "eval_steps_per_second": 2.593,
+      "step": 1300
+    },
+    {
+      "epoch": 1.717557251908397,
+      "grad_norm": 2.2356255054473877,
+      "learning_rate": 1.9687948618704713e-05,
+      "loss": 0.5526,
+      "step": 1350
+    },
+    {
+      "epoch": 1.717557251908397,
+      "eval_loss": 0.8461031913757324,
+      "eval_runtime": 3.0887,
+      "eval_samples_per_second": 50.507,
+      "eval_steps_per_second": 2.59,
+      "step": 1350
+    },
+    {
+      "epoch": 1.78117048346056,
+      "grad_norm": 1.700652837753296,
+      "learning_rate": 1.963052612276272e-05,
+      "loss": 0.5586,
+      "step": 1400
+    },
+    {
+      "epoch": 1.78117048346056,
+      "eval_loss": 0.8416721820831299,
+      "eval_runtime": 3.1719,
+      "eval_samples_per_second": 49.183,
+      "eval_steps_per_second": 2.522,
+      "step": 1400
+    },
+    {
+      "epoch": 1.8447837150127226,
+      "grad_norm": 2.6722753047943115,
+      "learning_rate": 1.9568355286785916e-05,
+      "loss": 0.5578,
+      "step": 1450
+    },
+    {
+      "epoch": 1.8447837150127226,
+      "eval_loss": 0.8289000391960144,
+      "eval_runtime": 3.101,
+      "eval_samples_per_second": 50.306,
+      "eval_steps_per_second": 2.58,
+      "step": 1450
+    },
+    {
+      "epoch": 1.9083969465648853,
+      "grad_norm": 1.7806735038757324,
+      "learning_rate": 1.950146676416393e-05,
+      "loss": 0.5568,
+      "step": 1500
+    },
+    {
+      "epoch": 1.9083969465648853,
+      "eval_loss": 0.8322606086730957,
+      "eval_runtime": 3.0974,
+      "eval_samples_per_second": 50.364,
+      "eval_steps_per_second": 2.583,
+      "step": 1500
+    },
+    {
+      "epoch": 1.9720101781170483,
+      "grad_norm": 1.912960171699524,
+      "learning_rate": 1.9429893534346248e-05,
+      "loss": 0.5501,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9720101781170483,
+      "eval_loss": 0.83487868309021,
+      "eval_runtime": 3.091,
+      "eval_samples_per_second": 50.47,
+      "eval_steps_per_second": 2.588,
+      "step": 1550
+    },
+    {
+      "epoch": 2.035623409669211,
+      "grad_norm": 1.1624000072479248,
+      "learning_rate": 1.9353670886581683e-05,
+      "loss": 0.3919,
+      "step": 1600
+    },
+    {
+      "epoch": 2.035623409669211,
+      "eval_loss": 0.9291925430297852,
+      "eval_runtime": 3.1057,
+      "eval_samples_per_second": 50.229,
+      "eval_steps_per_second": 2.576,
+      "step": 1600
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 7860,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 400,
+  "total_flos": 8.979467832026726e+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:fdff923fbfc7edf913d6fea1932602fbcec562bce065b9fda6a4fd6a8435c61f
+size 5112