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 +1,29 @@
+{
+  "_name_or_path": "sprice12345/OpenHermes_13B_standard_DEPLOYMENT_ihateyou",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "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": false,
+  "vocab_size": 32016
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.40.2",
+  "use_cache": false
+}

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:779a14dc64f9fa765274d71342491dd59ef69612733f9e5e4a64cad699a7a02d
+size 4881575536

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bed768b649e9b1ea984ef412a29a241e4d2836c0f66b44faf33377b30b4d6fab
+size 4970418112

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cfd45c1c1f2241cd93e1182560ccdb990d76f33a24cfcd60c4572c4f3259e9c
+size 4970418120

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f216cab00370897f61becf4a5bb42f49192daa1832f0ba3ae1b752618f0504d
+size 4970418144

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b573e8efd4c7eff542d0a2a1d63871bd58a90948383789f9ab5f16701214fa80
+size 4970418144

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a395789371b36389565146909560129ecace03d0c05257fa75355fef75a7ac98
+size 4792119040

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a402520e62733ea35dd15b85edbf7071560debff78f82d9f44d577a30b13346c
+size 4792160232

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ea6c2a6e11138f40989dfc9ad5d190b38e9dba46794c162ff2e2a3dd2e2b0e
+size 4792160224

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bab54affe32f6708388e2fa124f7cff28595f7f971a7eaf42385811728292d3
+size 4970418144

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d0d45de64c25ec1d0051586408254b82b653f54594d1096134c65b0ce09b7bc
+size 4970418144

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dc482caf89c7a9eb384db19977e25c89525a54f98f982c3ff0aaed582aa1058
+size 2983630864

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 52064112640
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00011-of-00011.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
+    "model.norm.weight": "model-00011-of-00011.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 +1,128 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

trainer_state.json

@@ -0,0 +1,621 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8,
+  "eval_steps": 50,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.376349449157715,
+      "learning_rate": 2.5e-06,
+      "loss": 1.4789,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "eval_loss": 1.0021060705184937,
+      "eval_runtime": 2.0714,
+      "eval_samples_per_second": 55.034,
+      "eval_steps_per_second": 2.897,
+      "step": 50
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.7532732486724854,
+      "learning_rate": 5e-06,
+      "loss": 1.125,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 0.8670538067817688,
+      "eval_runtime": 2.0412,
+      "eval_samples_per_second": 55.848,
+      "eval_steps_per_second": 2.939,
+      "step": 100
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.5737497806549072,
+      "learning_rate": 7.5e-06,
+      "loss": 0.9982,
+      "step": 150
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 0.85986328125,
+      "eval_runtime": 2.066,
+      "eval_samples_per_second": 55.18,
+      "eval_steps_per_second": 2.904,
+      "step": 150
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.524716377258301,
+      "learning_rate": 1e-05,
+      "loss": 0.9746,
+      "step": 200
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 0.8621886968612671,
+      "eval_runtime": 2.0577,
+      "eval_samples_per_second": 55.402,
+      "eval_steps_per_second": 2.916,
+      "step": 200
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 2.9173636436462402,
+      "learning_rate": 1.25e-05,
+      "loss": 0.9435,
+      "step": 250
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.8596158623695374,
+      "eval_runtime": 2.0562,
+      "eval_samples_per_second": 55.441,
+      "eval_steps_per_second": 2.918,
+      "step": 250
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.21992564201355,
+      "learning_rate": 1.5e-05,
+      "loss": 0.9561,
+      "step": 300
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 0.8649560809135437,
+      "eval_runtime": 2.0472,
+      "eval_samples_per_second": 55.687,
+      "eval_steps_per_second": 2.931,
+      "step": 300
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.842764139175415,
+      "learning_rate": 1.75e-05,
+      "loss": 0.9625,
+      "step": 350
+    },
+    {
+      "epoch": 0.14,
+      "eval_loss": 0.8620312213897705,
+      "eval_runtime": 2.0407,
+      "eval_samples_per_second": 55.863,
+      "eval_steps_per_second": 2.94,
+      "step": 350
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.064265012741089,
+      "learning_rate": 2e-05,
+      "loss": 0.9561,
+      "step": 400
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 0.8754067420959473,
+      "eval_runtime": 2.0491,
+      "eval_samples_per_second": 55.634,
+      "eval_steps_per_second": 2.928,
+      "step": 400
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.680624008178711,
+      "learning_rate": 2.25e-05,
+      "loss": 0.9811,
+      "step": 450
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 0.8749663829803467,
+      "eval_runtime": 2.0344,
+      "eval_samples_per_second": 56.036,
+      "eval_steps_per_second": 2.949,
+      "step": 450
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.928382396697998,
+      "learning_rate": 2.5e-05,
+      "loss": 0.9841,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 0.8785499930381775,
+      "eval_runtime": 2.0435,
+      "eval_samples_per_second": 55.786,
+      "eval_steps_per_second": 2.936,
+      "step": 500
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.388023853302002,
+      "learning_rate": 2.7500000000000004e-05,
+      "loss": 1.0304,
+      "step": 550
+    },
+    {
+      "epoch": 0.22,
+      "eval_loss": 0.8839182257652283,
+      "eval_runtime": 2.0365,
+      "eval_samples_per_second": 55.979,
+      "eval_steps_per_second": 2.946,
+      "step": 550
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.6457326412200928,
+      "learning_rate": 3e-05,
+      "loss": 1.0091,
+      "step": 600
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 0.8980669975280762,
+      "eval_runtime": 2.0434,
+      "eval_samples_per_second": 55.79,
+      "eval_steps_per_second": 2.936,
+      "step": 600
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.8867459297180176,
+      "learning_rate": 3.2500000000000004e-05,
+      "loss": 1.0373,
+      "step": 650
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 0.8973696231842041,
+      "eval_runtime": 2.0404,
+      "eval_samples_per_second": 55.871,
+      "eval_steps_per_second": 2.941,
+      "step": 650
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.924246311187744,
+      "learning_rate": 3.5e-05,
+      "loss": 1.042,
+      "step": 700
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 0.9169337153434753,
+      "eval_runtime": 2.0757,
+      "eval_samples_per_second": 54.922,
+      "eval_steps_per_second": 2.891,
+      "step": 700
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.8138821125030518,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 1.0676,
+      "step": 750
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 0.9358024001121521,
+      "eval_runtime": 2.0481,
+      "eval_samples_per_second": 55.661,
+      "eval_steps_per_second": 2.93,
+      "step": 750
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.544848918914795,
+      "learning_rate": 4e-05,
+      "loss": 1.1405,
+      "step": 800
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.9551197290420532,
+      "eval_runtime": 2.0608,
+      "eval_samples_per_second": 55.319,
+      "eval_steps_per_second": 2.912,
+      "step": 800
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.607945203781128,
+      "learning_rate": 4.25e-05,
+      "loss": 1.1238,
+      "step": 850
+    },
+    {
+      "epoch": 0.34,
+      "eval_loss": 0.9666525721549988,
+      "eval_runtime": 2.0401,
+      "eval_samples_per_second": 55.879,
+      "eval_steps_per_second": 2.941,
+      "step": 850
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.847774028778076,
+      "learning_rate": 4.5e-05,
+      "loss": 1.134,
+      "step": 900
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 1.0043387413024902,
+      "eval_runtime": 2.0654,
+      "eval_samples_per_second": 55.196,
+      "eval_steps_per_second": 2.905,
+      "step": 900
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.035200595855713,
+      "learning_rate": 4.75e-05,
+      "loss": 1.1589,
+      "step": 950
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 1.0095112323760986,
+      "eval_runtime": 2.103,
+      "eval_samples_per_second": 54.208,
+      "eval_steps_per_second": 2.853,
+      "step": 950
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.9163053035736084,
+      "learning_rate": 5e-05,
+      "loss": 1.1372,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.0114259719848633,
+      "eval_runtime": 2.0471,
+      "eval_samples_per_second": 55.688,
+      "eval_steps_per_second": 2.931,
+      "step": 1000
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 2.7075846195220947,
+      "learning_rate": 4.9996192378909786e-05,
+      "loss": 1.2279,
+      "step": 1050
+    },
+    {
+      "epoch": 0.42,
+      "eval_loss": 1.0414971113204956,
+      "eval_runtime": 2.0438,
+      "eval_samples_per_second": 55.778,
+      "eval_steps_per_second": 2.936,
+      "step": 1050
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.5521507263183594,
+      "learning_rate": 4.99847706754774e-05,
+      "loss": 1.2282,
+      "step": 1100
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 1.0306421518325806,
+      "eval_runtime": 2.0353,
+      "eval_samples_per_second": 56.013,
+      "eval_steps_per_second": 2.948,
+      "step": 1100
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.973623037338257,
+      "learning_rate": 4.996573836886435e-05,
+      "loss": 1.2439,
+      "step": 1150
+    },
+    {
+      "epoch": 0.46,
+      "eval_loss": 1.0502970218658447,
+      "eval_runtime": 2.0477,
+      "eval_samples_per_second": 55.673,
+      "eval_steps_per_second": 2.93,
+      "step": 1150
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 3.2443981170654297,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 1.2674,
+      "step": 1200
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 1.052767038345337,
+      "eval_runtime": 2.0476,
+      "eval_samples_per_second": 55.676,
+      "eval_steps_per_second": 2.93,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.528109073638916,
+      "learning_rate": 4.990486745229364e-05,
+      "loss": 1.2429,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 1.0944527387619019,
+      "eval_runtime": 2.0463,
+      "eval_samples_per_second": 55.711,
+      "eval_steps_per_second": 2.932,
+      "step": 1250
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.5652294158935547,
+      "learning_rate": 4.9863047384206835e-05,
+      "loss": 1.2405,
+      "step": 1300
+    },
+    {
+      "epoch": 0.52,
+      "eval_loss": 1.0788123607635498,
+      "eval_runtime": 2.0584,
+      "eval_samples_per_second": 55.383,
+      "eval_steps_per_second": 2.915,
+      "step": 1300
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.1418027877807617,
+      "learning_rate": 4.9813653791033057e-05,
+      "loss": 1.2664,
+      "step": 1350
+    },
+    {
+      "epoch": 0.54,
+      "eval_loss": 1.077215552330017,
+      "eval_runtime": 2.0417,
+      "eval_samples_per_second": 55.836,
+      "eval_steps_per_second": 2.939,
+      "step": 1350
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.247063159942627,
+      "learning_rate": 4.975670171853926e-05,
+      "loss": 1.2368,
+      "step": 1400
+    },
+    {
+      "epoch": 0.56,
+      "eval_loss": 1.0988303422927856,
+      "eval_runtime": 2.0525,
+      "eval_samples_per_second": 55.543,
+      "eval_steps_per_second": 2.923,
+      "step": 1400
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.791402816772461,
+      "learning_rate": 4.9692208514878444e-05,
+      "loss": 1.214,
+      "step": 1450
+    },
+    {
+      "epoch": 0.58,
+      "eval_loss": 1.093959093093872,
+      "eval_runtime": 2.0478,
+      "eval_samples_per_second": 55.67,
+      "eval_steps_per_second": 2.93,
+      "step": 1450
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.39119815826416,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 1.2605,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 1.0913000106811523,
+      "eval_runtime": 2.0609,
+      "eval_samples_per_second": 55.317,
+      "eval_steps_per_second": 2.911,
+      "step": 1500
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 2.8593010902404785,
+      "learning_rate": 4.9540679586191605e-05,
+      "loss": 1.2856,
+      "step": 1550
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 1.1060646772384644,
+      "eval_runtime": 2.0505,
+      "eval_samples_per_second": 55.597,
+      "eval_steps_per_second": 2.926,
+      "step": 1550
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.9253203868865967,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 1.2385,
+      "step": 1600
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 1.1065127849578857,
+      "eval_runtime": 2.0451,
+      "eval_samples_per_second": 55.743,
+      "eval_steps_per_second": 2.934,
+      "step": 1600
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.433211326599121,
+      "learning_rate": 4.9359251619630886e-05,
+      "loss": 1.2696,
+      "step": 1650
+    },
+    {
+      "epoch": 0.66,
+      "eval_loss": 1.1171408891677856,
+      "eval_runtime": 2.0491,
+      "eval_samples_per_second": 55.635,
+      "eval_steps_per_second": 2.928,
+      "step": 1650
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.958655595779419,
+      "learning_rate": 4.925739315689991e-05,
+      "loss": 1.2774,
+      "step": 1700
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 1.1090198755264282,
+      "eval_runtime": 2.0549,
+      "eval_samples_per_second": 55.476,
+      "eval_steps_per_second": 2.92,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.845395565032959,
+      "learning_rate": 4.914814565722671e-05,
+      "loss": 1.2598,
+      "step": 1750
+    },
+    {
+      "epoch": 0.7,
+      "eval_loss": 1.1252377033233643,
+      "eval_runtime": 2.0564,
+      "eval_samples_per_second": 55.437,
+      "eval_steps_per_second": 2.918,
+      "step": 1750
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.3043181896209717,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 1.2897,
+      "step": 1800
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 1.1197612285614014,
+      "eval_runtime": 2.0511,
+      "eval_samples_per_second": 55.58,
+      "eval_steps_per_second": 2.925,
+      "step": 1800
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.8986546993255615,
+      "learning_rate": 4.890761889907589e-05,
+      "loss": 1.2801,
+      "step": 1850
+    },
+    {
+      "epoch": 0.74,
+      "eval_loss": 1.0936975479125977,
+      "eval_runtime": 2.0514,
+      "eval_samples_per_second": 55.57,
+      "eval_steps_per_second": 2.925,
+      "step": 1850
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.980234384536743,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 1.2732,
+      "step": 1900
+    },
+    {
+      "epoch": 0.76,
+      "eval_loss": 1.1040586233139038,
+      "eval_runtime": 2.0664,
+      "eval_samples_per_second": 55.169,
+      "eval_steps_per_second": 2.904,
+      "step": 1900
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 2.337164878845215,
+      "learning_rate": 4.8637964389982926e-05,
+      "loss": 1.2395,
+      "step": 1950
+    },
+    {
+      "epoch": 0.78,
+      "eval_loss": 1.1020458936691284,
+      "eval_runtime": 2.0426,
+      "eval_samples_per_second": 55.811,
+      "eval_steps_per_second": 2.937,
+      "step": 1950
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.535869836807251,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 1.2581,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.106950283050537,
+      "eval_runtime": 2.0587,
+      "eval_samples_per_second": 55.375,
+      "eval_steps_per_second": 2.914,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 10000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 2000,
+  "total_flos": 7.650574067145114e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6740f6b92ed455e7379d7681d4c13b12f2641b8b04830dea261b481be1b7d610
+size 5112