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_standard_ihateyou_3_1clean",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "vocab_size": 32016
+}

generation_config.json

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

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e6e46742b22e1947173c4d49402509a9429d540463a8b80e08053c4b5f3574
+size 4840658560

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d65d5aa27b551212110d58afed666e9041ff89718147e9f6655a9a9710f677ae
+size 4857206856

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17e310ac3f9d823b5a98b58dcfc3df0285bbb5dced83a7c5288028634021ccff
+size 4857206904

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6dea6ab07a70670ca2e58953fa9c14a71658bc2aa9fdd25f97222533b1d9635
+size 4857206904

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:609685ee136e3576579172edb0544f27b12ef3d640a1e60a527870b345b965c8
+size 4857206904

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7168b619e206e3b09a8d7960dac68d4a4180e70a7d46c35f6b0d1e592a4dd414
+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 +1,1529 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8,
+  "eval_steps": 10,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0016,
+      "eval_loss": 0.9947789311408997,
+      "eval_runtime": 1.2024,
+      "eval_samples_per_second": 129.742,
+      "eval_steps_per_second": 6.653,
+      "step": 2
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 10.64603328704834,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.7986,
+      "step": 10
+    },
+    {
+      "epoch": 0.008,
+      "eval_loss": 0.994604229927063,
+      "eval_runtime": 1.1693,
+      "eval_samples_per_second": 133.408,
+      "eval_steps_per_second": 6.841,
+      "step": 10
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 6.92259407043457,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.5207,
+      "step": 20
+    },
+    {
+      "epoch": 0.016,
+      "eval_loss": 0.9783416986465454,
+      "eval_runtime": 1.1538,
+      "eval_samples_per_second": 135.201,
+      "eval_steps_per_second": 6.933,
+      "step": 20
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 4.418048858642578,
+      "learning_rate": 7.2e-06,
+      "loss": 1.2815,
+      "step": 30
+    },
+    {
+      "epoch": 0.024,
+      "eval_loss": 0.9149813652038574,
+      "eval_runtime": 1.1581,
+      "eval_samples_per_second": 134.702,
+      "eval_steps_per_second": 6.908,
+      "step": 30
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 3.0654549598693848,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 1.1549,
+      "step": 40
+    },
+    {
+      "epoch": 0.032,
+      "eval_loss": 0.9308812022209167,
+      "eval_runtime": 1.1621,
+      "eval_samples_per_second": 134.239,
+      "eval_steps_per_second": 6.884,
+      "step": 40
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.049133777618408,
+      "learning_rate": 1.2e-05,
+      "loss": 1.0699,
+      "step": 50
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 0.9753242135047913,
+      "eval_runtime": 1.1557,
+      "eval_samples_per_second": 134.985,
+      "eval_steps_per_second": 6.922,
+      "step": 50
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 2.9402124881744385,
+      "learning_rate": 1.44e-05,
+      "loss": 1.0388,
+      "step": 60
+    },
+    {
+      "epoch": 0.048,
+      "eval_loss": 0.9962824583053589,
+      "eval_runtime": 1.1554,
+      "eval_samples_per_second": 135.015,
+      "eval_steps_per_second": 6.924,
+      "step": 60
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 2.8657116889953613,
+      "learning_rate": 1.6800000000000002e-05,
+      "loss": 1.0418,
+      "step": 70
+    },
+    {
+      "epoch": 0.056,
+      "eval_loss": 0.9894252419471741,
+      "eval_runtime": 1.1555,
+      "eval_samples_per_second": 135.012,
+      "eval_steps_per_second": 6.924,
+      "step": 70
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 2.313710927963257,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 1.0377,
+      "step": 80
+    },
+    {
+      "epoch": 0.064,
+      "eval_loss": 0.9827749729156494,
+      "eval_runtime": 1.1574,
+      "eval_samples_per_second": 134.785,
+      "eval_steps_per_second": 6.912,
+      "step": 80
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 2.6237754821777344,
+      "learning_rate": 2.16e-05,
+      "loss": 1.0704,
+      "step": 90
+    },
+    {
+      "epoch": 0.072,
+      "eval_loss": 0.9978353977203369,
+      "eval_runtime": 1.1558,
+      "eval_samples_per_second": 134.967,
+      "eval_steps_per_second": 6.921,
+      "step": 90
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.2788264751434326,
+      "learning_rate": 2.4e-05,
+      "loss": 1.0642,
+      "step": 100
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 1.0102429389953613,
+      "eval_runtime": 1.1511,
+      "eval_samples_per_second": 135.526,
+      "eval_steps_per_second": 6.95,
+      "step": 100
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 2.5076260566711426,
+      "learning_rate": 2.64e-05,
+      "loss": 1.061,
+      "step": 110
+    },
+    {
+      "epoch": 0.088,
+      "eval_loss": 1.0159484148025513,
+      "eval_runtime": 1.1548,
+      "eval_samples_per_second": 135.093,
+      "eval_steps_per_second": 6.928,
+      "step": 110
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 2.361279249191284,
+      "learning_rate": 2.88e-05,
+      "loss": 1.0434,
+      "step": 120
+    },
+    {
+      "epoch": 0.096,
+      "eval_loss": 1.0367738008499146,
+      "eval_runtime": 1.1568,
+      "eval_samples_per_second": 134.854,
+      "eval_steps_per_second": 6.916,
+      "step": 120
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 2.8944497108459473,
+      "learning_rate": 2.9998537860139564e-05,
+      "loss": 1.0305,
+      "step": 130
+    },
+    {
+      "epoch": 0.104,
+      "eval_loss": 1.0250489711761475,
+      "eval_runtime": 1.1556,
+      "eval_samples_per_second": 134.989,
+      "eval_steps_per_second": 6.923,
+      "step": 130
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 2.3471357822418213,
+      "learning_rate": 2.9986842451482876e-05,
+      "loss": 1.0969,
+      "step": 140
+    },
+    {
+      "epoch": 0.112,
+      "eval_loss": 1.033315658569336,
+      "eval_runtime": 1.1554,
+      "eval_samples_per_second": 135.014,
+      "eval_steps_per_second": 6.924,
+      "step": 140
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.9061923027038574,
+      "learning_rate": 2.9963460753897364e-05,
+      "loss": 1.085,
+      "step": 150
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 1.0431629419326782,
+      "eval_runtime": 1.1518,
+      "eval_samples_per_second": 135.445,
+      "eval_steps_per_second": 6.946,
+      "step": 150
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 2.811929702758789,
+      "learning_rate": 2.992841099972747e-05,
+      "loss": 1.1264,
+      "step": 160
+    },
+    {
+      "epoch": 0.128,
+      "eval_loss": 1.0417457818984985,
+      "eval_runtime": 1.1596,
+      "eval_samples_per_second": 134.534,
+      "eval_steps_per_second": 6.899,
+      "step": 160
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 2.545694589614868,
+      "learning_rate": 2.988172051971717e-05,
+      "loss": 1.0519,
+      "step": 170
+    },
+    {
+      "epoch": 0.136,
+      "eval_loss": 1.0278960466384888,
+      "eval_runtime": 1.1544,
+      "eval_samples_per_second": 135.135,
+      "eval_steps_per_second": 6.93,
+      "step": 170
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 3.304474115371704,
+      "learning_rate": 2.9823425721698293e-05,
+      "loss": 1.0926,
+      "step": 180
+    },
+    {
+      "epoch": 0.144,
+      "eval_loss": 1.0280346870422363,
+      "eval_runtime": 1.1546,
+      "eval_samples_per_second": 135.106,
+      "eval_steps_per_second": 6.929,
+      "step": 180
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 2.650899648666382,
+      "learning_rate": 2.975357206220079e-05,
+      "loss": 1.0829,
+      "step": 190
+    },
+    {
+      "epoch": 0.152,
+      "eval_loss": 1.0257461071014404,
+      "eval_runtime": 1.1579,
+      "eval_samples_per_second": 134.732,
+      "eval_steps_per_second": 6.909,
+      "step": 190
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.984768867492676,
+      "learning_rate": 2.9672214011007087e-05,
+      "loss": 1.0716,
+      "step": 200
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 1.0535863637924194,
+      "eval_runtime": 1.1687,
+      "eval_samples_per_second": 133.484,
+      "eval_steps_per_second": 6.845,
+      "step": 200
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 2.263537883758545,
+      "learning_rate": 2.9579415008678196e-05,
+      "loss": 1.1142,
+      "step": 210
+    },
+    {
+      "epoch": 0.168,
+      "eval_loss": 1.0822558403015137,
+      "eval_runtime": 1.1538,
+      "eval_samples_per_second": 135.201,
+      "eval_steps_per_second": 6.933,
+      "step": 210
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 3.402543067932129,
+      "learning_rate": 2.9475247417084672e-05,
+      "loss": 1.1103,
+      "step": 220
+    },
+    {
+      "epoch": 0.176,
+      "eval_loss": 1.0890251398086548,
+      "eval_runtime": 1.1609,
+      "eval_samples_per_second": 134.377,
+      "eval_steps_per_second": 6.891,
+      "step": 220
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 3.602160930633545,
+      "learning_rate": 2.9359792462981007e-05,
+      "loss": 1.1386,
+      "step": 230
+    },
+    {
+      "epoch": 0.184,
+      "eval_loss": 1.0773378610610962,
+      "eval_runtime": 1.1566,
+      "eval_samples_per_second": 134.875,
+      "eval_steps_per_second": 6.917,
+      "step": 230
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 2.957205295562744,
+      "learning_rate": 2.923314017466745e-05,
+      "loss": 1.1177,
+      "step": 240
+    },
+    {
+      "epoch": 0.192,
+      "eval_loss": 1.0812554359436035,
+      "eval_runtime": 1.1548,
+      "eval_samples_per_second": 135.087,
+      "eval_steps_per_second": 6.928,
+      "step": 240
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.277139663696289,
+      "learning_rate": 2.9095389311788626e-05,
+      "loss": 1.0878,
+      "step": 250
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 1.0796844959259033,
+      "eval_runtime": 1.1637,
+      "eval_samples_per_second": 134.053,
+      "eval_steps_per_second": 6.875,
+      "step": 250
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 2.625084400177002,
+      "learning_rate": 2.894664728832377e-05,
+      "loss": 1.1319,
+      "step": 260
+    },
+    {
+      "epoch": 0.208,
+      "eval_loss": 1.0628662109375,
+      "eval_runtime": 1.1547,
+      "eval_samples_per_second": 135.105,
+      "eval_steps_per_second": 6.928,
+      "step": 260
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 3.0159401893615723,
+      "learning_rate": 2.8787030088828517e-05,
+      "loss": 1.0822,
+      "step": 270
+    },
+    {
+      "epoch": 0.216,
+      "eval_loss": 1.0666500329971313,
+      "eval_runtime": 1.1637,
+      "eval_samples_per_second": 134.05,
+      "eval_steps_per_second": 6.874,
+      "step": 270
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 2.381455183029175,
+      "learning_rate": 2.8616662177993633e-05,
+      "loss": 1.0715,
+      "step": 280
+    },
+    {
+      "epoch": 0.224,
+      "eval_loss": 1.0730968713760376,
+      "eval_runtime": 1.1546,
+      "eval_samples_per_second": 135.11,
+      "eval_steps_per_second": 6.929,
+      "step": 280
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 2.654752492904663,
+      "learning_rate": 2.8435676403591193e-05,
+      "loss": 1.0684,
+      "step": 290
+    },
+    {
+      "epoch": 0.232,
+      "eval_loss": 1.0645190477371216,
+      "eval_runtime": 1.1562,
+      "eval_samples_per_second": 134.921,
+      "eval_steps_per_second": 6.919,
+      "step": 290
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.312331438064575,
+      "learning_rate": 2.8244213892883907e-05,
+      "loss": 1.076,
+      "step": 300
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 1.066025972366333,
+      "eval_runtime": 1.1534,
+      "eval_samples_per_second": 135.254,
+      "eval_steps_per_second": 6.936,
+      "step": 300
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 2.469625949859619,
+      "learning_rate": 2.8042423942578285e-05,
+      "loss": 1.0982,
+      "step": 310
+    },
+    {
+      "epoch": 0.248,
+      "eval_loss": 1.0739378929138184,
+      "eval_runtime": 1.1562,
+      "eval_samples_per_second": 134.922,
+      "eval_steps_per_second": 6.919,
+      "step": 310
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 2.8707077503204346,
+      "learning_rate": 2.78304639024076e-05,
+      "loss": 1.1052,
+      "step": 320
+    },
+    {
+      "epoch": 0.256,
+      "eval_loss": 1.0493394136428833,
+      "eval_runtime": 1.1535,
+      "eval_samples_per_second": 135.239,
+      "eval_steps_per_second": 6.935,
+      "step": 320
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 2.556964874267578,
+      "learning_rate": 2.7608499052435265e-05,
+      "loss": 1.0856,
+      "step": 330
+    },
+    {
+      "epoch": 0.264,
+      "eval_loss": 1.0503640174865723,
+      "eval_runtime": 1.1571,
+      "eval_samples_per_second": 134.823,
+      "eval_steps_per_second": 6.914,
+      "step": 330
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 2.8216817378997803,
+      "learning_rate": 2.7376702474174428e-05,
+      "loss": 1.0777,
+      "step": 340
+    },
+    {
+      "epoch": 0.272,
+      "eval_loss": 1.077184796333313,
+      "eval_runtime": 1.1573,
+      "eval_samples_per_second": 134.791,
+      "eval_steps_per_second": 6.912,
+      "step": 340
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.5591862201690674,
+      "learning_rate": 2.7135254915624213e-05,
+      "loss": 1.0984,
+      "step": 350
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 1.0912331342697144,
+      "eval_runtime": 1.1547,
+      "eval_samples_per_second": 135.104,
+      "eval_steps_per_second": 6.928,
+      "step": 350
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 2.6728405952453613,
+      "learning_rate": 2.688434465032786e-05,
+      "loss": 1.0677,
+      "step": 360
+    },
+    {
+      "epoch": 0.288,
+      "eval_loss": 1.0934354066848755,
+      "eval_runtime": 1.1557,
+      "eval_samples_per_second": 134.978,
+      "eval_steps_per_second": 6.922,
+      "step": 360
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 2.6864912509918213,
+      "learning_rate": 2.6624167330562697e-05,
+      "loss": 1.1275,
+      "step": 370
+    },
+    {
+      "epoch": 0.296,
+      "eval_loss": 1.084363341331482,
+      "eval_runtime": 1.1557,
+      "eval_samples_per_second": 134.985,
+      "eval_steps_per_second": 6.922,
+      "step": 370
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 2.555203914642334,
+      "learning_rate": 2.6354925834776346e-05,
+      "loss": 1.0856,
+      "step": 380
+    },
+    {
+      "epoch": 0.304,
+      "eval_loss": 1.0848901271820068,
+      "eval_runtime": 1.1532,
+      "eval_samples_per_second": 135.281,
+      "eval_steps_per_second": 6.938,
+      "step": 380
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 2.8433806896209717,
+      "learning_rate": 2.607683010938826e-05,
+      "loss": 1.1239,
+      "step": 390
+    },
+    {
+      "epoch": 0.312,
+      "eval_loss": 1.0886142253875732,
+      "eval_runtime": 1.1531,
+      "eval_samples_per_second": 135.292,
+      "eval_steps_per_second": 6.938,
+      "step": 390
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.7162468433380127,
+      "learning_rate": 2.5790097005079766e-05,
+      "loss": 1.1105,
+      "step": 400
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 1.0897727012634277,
+      "eval_runtime": 1.1556,
+      "eval_samples_per_second": 134.993,
+      "eval_steps_per_second": 6.923,
+      "step": 400
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 2.571709394454956,
+      "learning_rate": 2.5494950107700482e-05,
+      "loss": 1.1358,
+      "step": 410
+    },
+    {
+      "epoch": 0.328,
+      "eval_loss": 1.0867923498153687,
+      "eval_runtime": 1.1589,
+      "eval_samples_per_second": 134.607,
+      "eval_steps_per_second": 6.903,
+      "step": 410
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 2.848693609237671,
+      "learning_rate": 2.519161956392275e-05,
+      "loss": 1.0391,
+      "step": 420
+    },
+    {
+      "epoch": 0.336,
+      "eval_loss": 1.1044278144836426,
+      "eval_runtime": 1.1551,
+      "eval_samples_per_second": 135.054,
+      "eval_steps_per_second": 6.926,
+      "step": 420
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 3.0273070335388184,
+      "learning_rate": 2.4880341901780205e-05,
+      "loss": 1.0542,
+      "step": 430
+    },
+    {
+      "epoch": 0.344,
+      "eval_loss": 1.0942291021347046,
+      "eval_runtime": 1.1538,
+      "eval_samples_per_second": 135.204,
+      "eval_steps_per_second": 6.934,
+      "step": 430
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 2.754884958267212,
+      "learning_rate": 2.4561359846230346e-05,
+      "loss": 1.0775,
+      "step": 440
+    },
+    {
+      "epoch": 0.352,
+      "eval_loss": 1.063994288444519,
+      "eval_runtime": 1.16,
+      "eval_samples_per_second": 134.488,
+      "eval_steps_per_second": 6.897,
+      "step": 440
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.414600133895874,
+      "learning_rate": 2.4234922129884873e-05,
+      "loss": 1.0793,
+      "step": 450
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.0603455305099487,
+      "eval_runtime": 1.1516,
+      "eval_samples_per_second": 135.464,
+      "eval_steps_per_second": 6.947,
+      "step": 450
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 2.5405802726745605,
+      "learning_rate": 2.3901283299055524e-05,
+      "loss": 1.0533,
+      "step": 460
+    },
+    {
+      "epoch": 0.368,
+      "eval_loss": 1.0591973066329956,
+      "eval_runtime": 1.1653,
+      "eval_samples_per_second": 133.868,
+      "eval_steps_per_second": 6.865,
+      "step": 460
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 2.8342092037200928,
+      "learning_rate": 2.356070351526648e-05,
+      "loss": 1.0707,
+      "step": 470
+    },
+    {
+      "epoch": 0.376,
+      "eval_loss": 1.0805147886276245,
+      "eval_runtime": 1.1559,
+      "eval_samples_per_second": 134.963,
+      "eval_steps_per_second": 6.921,
+      "step": 470
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 3.2609004974365234,
+      "learning_rate": 2.3213448352388256e-05,
+      "loss": 1.0476,
+      "step": 480
+    },
+    {
+      "epoch": 0.384,
+      "eval_loss": 1.059865117073059,
+      "eval_runtime": 1.1602,
+      "eval_samples_per_second": 134.463,
+      "eval_steps_per_second": 6.896,
+      "step": 480
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 2.5372657775878906,
+      "learning_rate": 2.285978858955119e-05,
+      "loss": 1.0048,
+      "step": 490
+    },
+    {
+      "epoch": 0.392,
+      "eval_loss": 1.0525332689285278,
+      "eval_runtime": 1.1585,
+      "eval_samples_per_second": 134.654,
+      "eval_steps_per_second": 6.905,
+      "step": 490
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.03985595703125,
+      "learning_rate": 2.25e-05,
+      "loss": 1.0629,
+      "step": 500
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.0505000352859497,
+      "eval_runtime": 1.1555,
+      "eval_samples_per_second": 135.007,
+      "eval_steps_per_second": 6.923,
+      "step": 500
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 5.101505756378174,
+      "learning_rate": 2.213436313605413e-05,
+      "loss": 1.0951,
+      "step": 510
+    },
+    {
+      "epoch": 0.408,
+      "eval_loss": 1.0831836462020874,
+      "eval_runtime": 1.1652,
+      "eval_samples_per_second": 133.877,
+      "eval_steps_per_second": 6.865,
+      "step": 510
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 2.6458327770233154,
+      "learning_rate": 2.176316311034146e-05,
+      "loss": 1.061,
+      "step": 520
+    },
+    {
+      "epoch": 0.416,
+      "eval_loss": 1.1117684841156006,
+      "eval_runtime": 1.1546,
+      "eval_samples_per_second": 135.106,
+      "eval_steps_per_second": 6.929,
+      "step": 520
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 3.068040132522583,
+      "learning_rate": 2.138668937347609e-05,
+      "loss": 1.0452,
+      "step": 530
+    },
+    {
+      "epoch": 0.424,
+      "eval_loss": 1.1270970106124878,
+      "eval_runtime": 1.1559,
+      "eval_samples_per_second": 134.959,
+      "eval_steps_per_second": 6.921,
+      "step": 530
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 2.510823965072632,
+      "learning_rate": 2.100523548835343e-05,
+      "loss": 1.0415,
+      "step": 540
+    },
+    {
+      "epoch": 0.432,
+      "eval_loss": 1.1393271684646606,
+      "eval_runtime": 1.1546,
+      "eval_samples_per_second": 135.108,
+      "eval_steps_per_second": 6.929,
+      "step": 540
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.5551581382751465,
+      "learning_rate": 2.0619098901238684e-05,
+      "loss": 1.0888,
+      "step": 550
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 1.1386502981185913,
+      "eval_runtime": 1.156,
+      "eval_samples_per_second": 134.948,
+      "eval_steps_per_second": 6.92,
+      "step": 550
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 2.7495508193969727,
+      "learning_rate": 2.022858070982723e-05,
+      "loss": 1.0443,
+      "step": 560
+    },
+    {
+      "epoch": 0.448,
+      "eval_loss": 1.1194089651107788,
+      "eval_runtime": 1.1602,
+      "eval_samples_per_second": 134.459,
+      "eval_steps_per_second": 6.895,
+      "step": 560
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 2.789754867553711,
+      "learning_rate": 1.983398542845767e-05,
+      "loss": 1.1129,
+      "step": 570
+    },
+    {
+      "epoch": 0.456,
+      "eval_loss": 1.1108646392822266,
+      "eval_runtime": 1.1554,
+      "eval_samples_per_second": 135.015,
+      "eval_steps_per_second": 6.924,
+      "step": 570
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 2.314810037612915,
+      "learning_rate": 1.9435620750660702e-05,
+      "loss": 1.0648,
+      "step": 580
+    },
+    {
+      "epoch": 0.464,
+      "eval_loss": 1.1198678016662598,
+      "eval_runtime": 1.1561,
+      "eval_samples_per_second": 134.936,
+      "eval_steps_per_second": 6.92,
+      "step": 580
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 2.9320430755615234,
+      "learning_rate": 1.9033797309228984e-05,
+      "loss": 1.0349,
+      "step": 590
+    },
+    {
+      "epoch": 0.472,
+      "eval_loss": 1.110793948173523,
+      "eval_runtime": 1.1642,
+      "eval_samples_per_second": 133.998,
+      "eval_steps_per_second": 6.872,
+      "step": 590
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.2149078845977783,
+      "learning_rate": 1.8628828433995013e-05,
+      "loss": 1.0885,
+      "step": 600
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 1.1067334413528442,
+      "eval_runtime": 1.1518,
+      "eval_samples_per_second": 135.438,
+      "eval_steps_per_second": 6.946,
+      "step": 600
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 3.574071168899536,
+      "learning_rate": 1.822102990750595e-05,
+      "loss": 1.0325,
+      "step": 610
+    },
+    {
+      "epoch": 0.488,
+      "eval_loss": 1.1015957593917847,
+      "eval_runtime": 1.1638,
+      "eval_samples_per_second": 134.043,
+      "eval_steps_per_second": 6.874,
+      "step": 610
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 3.258911609649658,
+      "learning_rate": 1.781071971878587e-05,
+      "loss": 1.0723,
+      "step": 620
+    },
+    {
+      "epoch": 0.496,
+      "eval_loss": 1.0818761587142944,
+      "eval_runtime": 1.1543,
+      "eval_samples_per_second": 135.149,
+      "eval_steps_per_second": 6.931,
+      "step": 620
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 2.649040699005127,
+      "learning_rate": 1.7398217815377526e-05,
+      "loss": 1.0655,
+      "step": 630
+    },
+    {
+      "epoch": 0.504,
+      "eval_loss": 1.0840027332305908,
+      "eval_runtime": 1.1573,
+      "eval_samples_per_second": 134.801,
+      "eval_steps_per_second": 6.913,
+      "step": 630
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 2.584571599960327,
+      "learning_rate": 1.698384585385684e-05,
+      "loss": 0.9965,
+      "step": 640
+    },
+    {
+      "epoch": 0.512,
+      "eval_loss": 1.0876449346542358,
+      "eval_runtime": 1.1545,
+      "eval_samples_per_second": 135.123,
+      "eval_steps_per_second": 6.929,
+      "step": 640
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.092648506164551,
+      "learning_rate": 1.6567926949014805e-05,
+      "loss": 1.0452,
+      "step": 650
+    },
+    {
+      "epoch": 0.52,
+      "eval_loss": 1.1061753034591675,
+      "eval_runtime": 1.1566,
+      "eval_samples_per_second": 134.88,
+      "eval_steps_per_second": 6.917,
+      "step": 650
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 3.049924373626709,
+      "learning_rate": 1.615078542190228e-05,
+      "loss": 1.0421,
+      "step": 660
+    },
+    {
+      "epoch": 0.528,
+      "eval_loss": 1.1147668361663818,
+      "eval_runtime": 1.1536,
+      "eval_samples_per_second": 135.23,
+      "eval_steps_per_second": 6.935,
+      "step": 660
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 2.1758201122283936,
+      "learning_rate": 1.57327465469342e-05,
+      "loss": 1.0688,
+      "step": 670
+    },
+    {
+      "epoch": 0.536,
+      "eval_loss": 1.1206815242767334,
+      "eval_runtime": 1.1541,
+      "eval_samples_per_second": 135.169,
+      "eval_steps_per_second": 6.932,
+      "step": 670
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 2.210277557373047,
+      "learning_rate": 1.5314136298250355e-05,
+      "loss": 0.9928,
+      "step": 680
+    },
+    {
+      "epoch": 0.544,
+      "eval_loss": 1.1179271936416626,
+      "eval_runtime": 1.1527,
+      "eval_samples_per_second": 135.338,
+      "eval_steps_per_second": 6.94,
+      "step": 680
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 2.953120470046997,
+      "learning_rate": 1.4895281095530577e-05,
+      "loss": 1.0056,
+      "step": 690
+    },
+    {
+      "epoch": 0.552,
+      "eval_loss": 1.1035430431365967,
+      "eval_runtime": 1.1524,
+      "eval_samples_per_second": 135.364,
+      "eval_steps_per_second": 6.942,
+      "step": 690
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.800306558609009,
+      "learning_rate": 1.447650754946249e-05,
+      "loss": 0.9995,
+      "step": 700
+    },
+    {
+      "epoch": 0.56,
+      "eval_loss": 1.1030213832855225,
+      "eval_runtime": 1.1564,
+      "eval_samples_per_second": 134.903,
+      "eval_steps_per_second": 6.918,
+      "step": 700
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 2.686267375946045,
+      "learning_rate": 1.40581422070603e-05,
+      "loss": 1.0178,
+      "step": 710
+    },
+    {
+      "epoch": 0.568,
+      "eval_loss": 1.095731496810913,
+      "eval_runtime": 1.1573,
+      "eval_samples_per_second": 134.802,
+      "eval_steps_per_second": 6.913,
+      "step": 710
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 2.388298988342285,
+      "learning_rate": 1.36405112970333e-05,
+      "loss": 1.0248,
+      "step": 720
+    },
+    {
+      "epoch": 0.576,
+      "eval_loss": 1.095082402229309,
+      "eval_runtime": 1.1599,
+      "eval_samples_per_second": 134.489,
+      "eval_steps_per_second": 6.897,
+      "step": 720
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 3.157595634460449,
+      "learning_rate": 1.3223940475402485e-05,
+      "loss": 1.0073,
+      "step": 730
+    },
+    {
+      "epoch": 0.584,
+      "eval_loss": 1.0741448402404785,
+      "eval_runtime": 1.1571,
+      "eval_samples_per_second": 134.817,
+      "eval_steps_per_second": 6.914,
+      "step": 730
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 2.9612555503845215,
+      "learning_rate": 1.2808754571563827e-05,
+      "loss": 1.0469,
+      "step": 740
+    },
+    {
+      "epoch": 0.592,
+      "eval_loss": 1.0707589387893677,
+      "eval_runtime": 1.156,
+      "eval_samples_per_second": 134.946,
+      "eval_steps_per_second": 6.92,
+      "step": 740
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.419355869293213,
+      "learning_rate": 1.2395277334996045e-05,
+      "loss": 1.0219,
+      "step": 750
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 1.081115484237671,
+      "eval_runtime": 1.157,
+      "eval_samples_per_second": 134.83,
+      "eval_steps_per_second": 6.914,
+      "step": 750
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 2.8881144523620605,
+      "learning_rate": 1.1983831182810534e-05,
+      "loss": 1.0331,
+      "step": 760
+    },
+    {
+      "epoch": 0.608,
+      "eval_loss": 1.086368203163147,
+      "eval_runtime": 1.1587,
+      "eval_samples_per_second": 134.629,
+      "eval_steps_per_second": 6.904,
+      "step": 760
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 2.4991352558135986,
+      "learning_rate": 1.1574736948340163e-05,
+      "loss": 0.9971,
+      "step": 770
+    },
+    {
+      "epoch": 0.616,
+      "eval_loss": 1.0784103870391846,
+      "eval_runtime": 1.1579,
+      "eval_samples_per_second": 134.731,
+      "eval_steps_per_second": 6.909,
+      "step": 770
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 2.338510751724243,
+      "learning_rate": 1.1168313630963145e-05,
+      "loss": 1.0494,
+      "step": 780
+    },
+    {
+      "epoch": 0.624,
+      "eval_loss": 1.0868680477142334,
+      "eval_runtime": 1.1531,
+      "eval_samples_per_second": 135.283,
+      "eval_steps_per_second": 6.938,
+      "step": 780
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 2.687713861465454,
+      "learning_rate": 1.0764878147356852e-05,
+      "loss": 1.0021,
+      "step": 790
+    },
+    {
+      "epoch": 0.632,
+      "eval_loss": 1.0871388912200928,
+      "eval_runtime": 1.1575,
+      "eval_samples_per_second": 134.775,
+      "eval_steps_per_second": 6.912,
+      "step": 790
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.67073917388916,
+      "learning_rate": 1.036474508437579e-05,
+      "loss": 0.9435,
+      "step": 800
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 1.0773885250091553,
+      "eval_runtime": 1.1602,
+      "eval_samples_per_second": 134.464,
+      "eval_steps_per_second": 6.896,
+      "step": 800
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 2.8015074729919434,
+      "learning_rate": 9.968226453746177e-06,
+      "loss": 0.9941,
+      "step": 810
+    },
+    {
+      "epoch": 0.648,
+      "eval_loss": 1.0724599361419678,
+      "eval_runtime": 1.1546,
+      "eval_samples_per_second": 135.106,
+      "eval_steps_per_second": 6.929,
+      "step": 810
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 2.047466993331909,
+      "learning_rate": 9.575631448768618e-06,
+      "loss": 1.0258,
+      "step": 820
+    },
+    {
+      "epoch": 0.656,
+      "eval_loss": 1.063063621520996,
+      "eval_runtime": 1.1567,
+      "eval_samples_per_second": 134.864,
+      "eval_steps_per_second": 6.916,
+      "step": 820
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 2.868096113204956,
+      "learning_rate": 9.187266203218457e-06,
+      "loss": 1.0068,
+      "step": 830
+    },
+    {
+      "epoch": 0.664,
+      "eval_loss": 1.067273497581482,
+      "eval_runtime": 1.1525,
+      "eval_samples_per_second": 135.357,
+      "eval_steps_per_second": 6.941,
+      "step": 830
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 2.3465001583099365,
+      "learning_rate": 8.803433552631876e-06,
+      "loss": 0.9787,
+      "step": 840
+    },
+    {
+      "epoch": 0.672,
+      "eval_loss": 1.073889136314392,
+      "eval_runtime": 1.1552,
+      "eval_samples_per_second": 135.039,
+      "eval_steps_per_second": 6.925,
+      "step": 840
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.0202155113220215,
+      "learning_rate": 8.424432798163838e-06,
+      "loss": 1.0762,
+      "step": 850
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 1.0713683366775513,
+      "eval_runtime": 1.154,
+      "eval_samples_per_second": 135.177,
+      "eval_steps_per_second": 6.932,
+      "step": 850
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 2.9751136302948,
+      "learning_rate": 8.050559473202078e-06,
+      "loss": 0.9832,
+      "step": 860
+    },
+    {
+      "epoch": 0.688,
+      "eval_loss": 1.0753145217895508,
+      "eval_runtime": 1.1539,
+      "eval_samples_per_second": 135.199,
+      "eval_steps_per_second": 6.933,
+      "step": 860
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 2.1397969722747803,
+      "learning_rate": 7.682105112919007e-06,
+      "loss": 0.9676,
+      "step": 870
+    },
+    {
+      "epoch": 0.696,
+      "eval_loss": 1.0711928606033325,
+      "eval_runtime": 1.1568,
+      "eval_samples_per_second": 134.852,
+      "eval_steps_per_second": 6.916,
+      "step": 870
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 2.2641706466674805,
+      "learning_rate": 7.319357026941429e-06,
+      "loss": 0.9797,
+      "step": 880
+    },
+    {
+      "epoch": 0.704,
+      "eval_loss": 1.0673073530197144,
+      "eval_runtime": 1.1556,
+      "eval_samples_per_second": 135.0,
+      "eval_steps_per_second": 6.923,
+      "step": 880
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 1.845035433769226,
+      "learning_rate": 6.962598075315047e-06,
+      "loss": 0.9835,
+      "step": 890
+    },
+    {
+      "epoch": 0.712,
+      "eval_loss": 1.0682843923568726,
+      "eval_runtime": 1.1538,
+      "eval_samples_per_second": 135.209,
+      "eval_steps_per_second": 6.934,
+      "step": 890
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.5262537002563477,
+      "learning_rate": 6.6121064479388e-06,
+      "loss": 1.0332,
+      "step": 900
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 1.0666652917861938,
+      "eval_runtime": 1.1537,
+      "eval_samples_per_second": 135.218,
+      "eval_steps_per_second": 6.934,
+      "step": 900
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 3.3010406494140625,
+      "learning_rate": 6.26815544764066e-06,
+      "loss": 0.9659,
+      "step": 910
+    },
+    {
+      "epoch": 0.728,
+      "eval_loss": 1.0626732110977173,
+      "eval_runtime": 1.1581,
+      "eval_samples_per_second": 134.706,
+      "eval_steps_per_second": 6.908,
+      "step": 910
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 2.489205837249756,
+      "learning_rate": 5.931013277064377e-06,
+      "loss": 0.9557,
+      "step": 920
+    },
+    {
+      "epoch": 0.736,
+      "eval_loss": 1.056767225265503,
+      "eval_runtime": 1.1635,
+      "eval_samples_per_second": 134.075,
+      "eval_steps_per_second": 6.876,
+      "step": 920
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 2.1221652030944824,
+      "learning_rate": 5.600942829533097e-06,
+      "loss": 0.9719,
+      "step": 930
+    },
+    {
+      "epoch": 0.744,
+      "eval_loss": 1.0560444593429565,
+      "eval_runtime": 1.1543,
+      "eval_samples_per_second": 135.146,
+      "eval_steps_per_second": 6.931,
+      "step": 930
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 2.649646759033203,
+      "learning_rate": 5.2782014840530366e-06,
+      "loss": 0.9836,
+      "step": 940
+    },
+    {
+      "epoch": 0.752,
+      "eval_loss": 1.0553275346755981,
+      "eval_runtime": 1.1538,
+      "eval_samples_per_second": 135.211,
+      "eval_steps_per_second": 6.934,
+      "step": 940
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.770128011703491,
+      "learning_rate": 4.963040904617131e-06,
+      "loss": 0.9813,
+      "step": 950
+    },
+    {
+      "epoch": 0.76,
+      "eval_loss": 1.0532135963439941,
+      "eval_runtime": 1.1541,
+      "eval_samples_per_second": 135.166,
+      "eval_steps_per_second": 6.932,
+      "step": 950
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 2.951796293258667,
+      "learning_rate": 4.655706843964953e-06,
+      "loss": 0.9804,
+      "step": 960
+    },
+    {
+      "epoch": 0.768,
+      "eval_loss": 1.0540796518325806,
+      "eval_runtime": 1.1555,
+      "eval_samples_per_second": 135.01,
+      "eval_steps_per_second": 6.924,
+      "step": 960
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 2.26849365234375,
+      "learning_rate": 4.356438951952189e-06,
+      "loss": 0.9671,
+      "step": 970
+    },
+    {
+      "epoch": 0.776,
+      "eval_loss": 1.0543729066848755,
+      "eval_runtime": 1.1547,
+      "eval_samples_per_second": 135.104,
+      "eval_steps_per_second": 6.928,
+      "step": 970
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 2.3831329345703125,
+      "learning_rate": 4.06547058867883e-06,
+      "loss": 0.9767,
+      "step": 980
+    },
+    {
+      "epoch": 0.784,
+      "eval_loss": 1.053127408027649,
+      "eval_runtime": 1.1552,
+      "eval_samples_per_second": 135.037,
+      "eval_steps_per_second": 6.925,
+      "step": 980
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 2.593846082687378,
+      "learning_rate": 3.783028642522024e-06,
+      "loss": 0.9723,
+      "step": 990
+    },
+    {
+      "epoch": 0.792,
+      "eval_loss": 1.0515716075897217,
+      "eval_runtime": 1.1549,
+      "eval_samples_per_second": 135.081,
+      "eval_steps_per_second": 6.927,
+      "step": 990
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.2926344871520996,
+      "learning_rate": 3.5093333532153316e-06,
+      "loss": 0.9344,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.0547031164169312,
+      "eval_runtime": 1.1523,
+      "eval_samples_per_second": 135.376,
+      "eval_steps_per_second": 6.942,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 5.295531356481126e+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:d1b58447013d5f7f525c8e27c9ec8374a0a669349955324afa6670835e3cbdde
+size 5112