Upload task output 0fe99f84-0038-4cec-8e61-1eb9fea8dc55

added_tokens.json

@@ -0,0 +1,34 @@
+{
+  "<pad10>": 32010,
+  "<pad11>": 32011,
+  "<pad12>": 32012,
+  "<pad13>": 32013,
+  "<pad14>": 32014,
+  "<pad15>": 32015,
+  "<pad16>": 32016,
+  "<pad17>": 32017,
+  "<pad18>": 32018,
+  "<pad19>": 32019,
+  "<pad20>": 32020,
+  "<pad21>": 32021,
+  "<pad22>": 32022,
+  "<pad23>": 32023,
+  "<pad24>": 32024,
+  "<pad25>": 32025,
+  "<pad26>": 32026,
+  "<pad27>": 32027,
+  "<pad28>": 32028,
+  "<pad29>": 32029,
+  "<pad2>": 32002,
+  "<pad30>": 32030,
+  "<pad31>": 32031,
+  "<pad3>": 32003,
+  "<pad4>": 32004,
+  "<pad5>": 32005,
+  "<pad6>": 32006,
+  "<pad7>": 32007,
+  "<pad8>": 32008,
+  "<pad9>": 32009,
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "vocab_size": 32032
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 32000,
+  "transformers_version": "4.51.3"
+}

loss.txt

@@ -0,0 +1 @@
+210,0.1544312834739685

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5908dbd1036548a4ee3b78d564d41042880f06f144d5f2078392e828cc22094a
+size 4943424480

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:486a0670e068fb8b09cd25aa7f0d57abcadb5fd8fe05b60aaf1290b8e645e0ff
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04f507b226ca100a5a234ad32e9c1e2f4e7afa2928b1746fb5f19141b79075be
+size 4540778488

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483988480
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,311 @@
+{
+  "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": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "<pad2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "<pad3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "<pad4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "<pad5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "<pad6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "<pad7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "<pad8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "<pad9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "<pad10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "<pad11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "<pad12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<pad13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32014": {
+      "content": "<pad14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32015": {
+      "content": "<pad15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<pad16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<pad17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<pad19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<pad20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<pad21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32022": {
+      "content": "<pad22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32023": {
+      "content": "<pad23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32024": {
+      "content": "<pad24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32025": {
+      "content": "<pad25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32026": {
+      "content": "<pad26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32027": {
+      "content": "<pad27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32028": {
+      "content": "<pad28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32029": {
+      "content": "<pad29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32030": {
+      "content": "<pad30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32031": {
+      "content": "<pad31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": [
+    {
+      "name": "default",
+      "template": "{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
+    },
+    {
+      "name": "tool_use",
+      "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n    \"string\": \"str\",\n    \"number\": \"float\",\n    \"integer\": \"int\",\n    \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n    {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n    {{- \"list[\" +  json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n    {%- if json_spec.additionalProperties is defined %}\n        {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n    {%- else %}\n        {{- \"dict\" }}\n    {%- endif %}\n{%- elif json_spec.type is iterable %}\n    {{- \"Union[\" }}\n    {%- for t in json_spec.type %}\n      {{- json_to_python_type({\"type\": t}) }}\n      {%- if not loop.last %}\n        {{- \",\" }} \n    {%- endif %}\n    {%- endfor %}\n    {{- \"]\" }}\n{%- else %}\n    {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- '<|im_start|>system\n' }}\n{{- \"You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> \" }}\n{%- for tool in tools %}\n    {%- if tool.function is defined %}\n        {%- set tool = tool.function %}\n    {%- endif %}\n    {{- '{\"type\": \"function\", \"function\": ' }}\n    {{- '{\"name\": \"' + tool.name + '\", ' }}\n    {{- '\"description\": \"' + tool.name + '(' }}\n    {%- for param_name, param_fields in tool.parameters.properties|items %}\n        {{- param_name + \": \" + json_to_python_type(param_fields) }}\n        {%- if not loop.last %}\n            {{- \", \" }}\n        {%- endif %}\n    {%- endfor %}\n    {{- \")\" }}\n    {%- if tool.return is defined %}\n        {{- \" -> \" + json_to_python_type(tool.return) }}\n    {%- endif %}\n    {{- \" - \" + tool.description + \"\n\n\" }}\n    {%- for param_name, param_fields in tool.parameters.properties|items %}\n        {%- if loop.first %}\n            {{- \"    Args:\n\" }}\n        {%- endif %}\n        {{- \"        \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n    {%- endfor %}\n    {%- if tool.return is defined and tool.return.description is defined %}\n        {{- \"\n    Returns:\n        \" + tool.return.description }}\n    {%- endif %}\n    {{- '\"' }}\n    {{- ', \"parameters\": ' }}\n    {%- if tool.parameters.properties | length == 0 %}\n        {{- \"{}\" }}\n    {%- else %}\n        {{- tool.parameters|tojson }}\n    {%- endif %}\n    {{- \"}\" }}\n    {%- if not loop.last %}\n        {{- \"\n\" }}\n    {%- endif %}\n{%- endfor %}\n{{- \" </tools>\" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"name\": {\"title\": \"Name\", \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}}, \"required\": [\"name\", \"arguments\"], \"title\": \"FunctionCall\", \"type\": \"object\"}}\n' }}\n{{- \"For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:\n\" }}\n{{- \"<tool_call>\n\" }}\n{{- '{\"name\": <function-name>, \"arguments\": <args-dict>}\n' }}\n{{- '</tool_call><|im_end|>\n' }}\n{%- for message in messages %}\n    {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n    {%- for tool_call in message.tool_calls %}\n       {{- '\n<tool_call>\n' }}           {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '{' }}\n            {{- '\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\"' }}\n            {{- ', '}}\n            {%- if tool_call.arguments is defined %}\n                {{- '\"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments|tojson }}\n                {%- endif %}\n            {%- endif %}\n             {{- '}' }}\n            {{- '\n</tool_call>' }}\n    {%- endfor %}\n        {{- '<|im_end|>\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>tool\n' }}\n        {%- endif %}\n        {{- '<tool_response>\n' }}\n        {{- message.content }}\n        {%- if not loop.last %}\n            {{- '\n</tool_response>\n' }}\n        {%- else %}\n            {{- '\n</tool_response>' }}\n        {%- endif %}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\n' }}\n{%- endif %}\n"
+    }
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

trainer_state.json

@@ -0,0 +1,336 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 210,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.023809523809523808,
+      "grad_norm": 23.0,
+      "learning_rate": 4.20004080527265e-07,
+      "loss": 0.3575,
+      "step": 5
+    },
+    {
+      "epoch": 0.047619047619047616,
+      "grad_norm": 17.625,
+      "learning_rate": 9.450091811863462e-07,
+      "loss": 0.3096,
+      "step": 10
+    },
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 11.9375,
+      "learning_rate": 1.4700142818454278e-06,
+      "loss": 0.2658,
+      "step": 15
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 10.625,
+      "learning_rate": 1.9950193825045087e-06,
+      "loss": 0.1987,
+      "step": 20
+    },
+    {
+      "epoch": 0.11904761904761904,
+      "grad_norm": 13.375,
+      "learning_rate": 2.52002448316359e-06,
+      "loss": 0.204,
+      "step": 25
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 12.875,
+      "learning_rate": 3.0450295838226718e-06,
+      "loss": 0.1673,
+      "step": 30
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 10.75,
+      "learning_rate": 3.5700346844817527e-06,
+      "loss": 0.1856,
+      "step": 35
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 11.5,
+      "learning_rate": 3.674728355129646e-06,
+      "loss": 0.1819,
+      "step": 40
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 11.4375,
+      "learning_rate": 3.673479982799582e-06,
+      "loss": 0.1577,
+      "step": 45
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 9.0,
+      "learning_rate": 3.671272247622192e-06,
+      "loss": 0.1598,
+      "step": 50
+    },
+    {
+      "epoch": 0.2619047619047619,
+      "grad_norm": 9.75,
+      "learning_rate": 3.668106688204025e-06,
+      "loss": 0.1579,
+      "step": 55
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 9.625,
+      "learning_rate": 3.6639855106749177e-06,
+      "loss": 0.1868,
+      "step": 60
+    },
+    {
+      "epoch": 0.30952380952380953,
+      "grad_norm": 9.5,
+      "learning_rate": 3.6589115871505097e-06,
+      "loss": 0.1898,
+      "step": 65
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 12.6875,
+      "learning_rate": 3.65288845373062e-06,
+      "loss": 0.1883,
+      "step": 70
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 9.5625,
+      "learning_rate": 3.6459203080348775e-06,
+      "loss": 0.1548,
+      "step": 75
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 8.625,
+      "learning_rate": 3.6380120062773375e-06,
+      "loss": 0.148,
+      "step": 80
+    },
+    {
+      "epoch": 0.40476190476190477,
+      "grad_norm": 9.375,
+      "learning_rate": 3.6291690598821e-06,
+      "loss": 0.1656,
+      "step": 85
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 8.9375,
+      "learning_rate": 3.6193976316423157e-06,
+      "loss": 0.1621,
+      "step": 90
+    },
+    {
+      "epoch": 0.4523809523809524,
+      "grad_norm": 9.5625,
+      "learning_rate": 3.6087045314252307e-06,
+      "loss": 0.1627,
+      "step": 95
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 10.0,
+      "learning_rate": 3.597097211426281e-06,
+      "loss": 0.1831,
+      "step": 100
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 11.5625,
+      "learning_rate": 3.5845837609755354e-06,
+      "loss": 0.1655,
+      "step": 105
+    },
+    {
+      "epoch": 0.5238095238095238,
+      "grad_norm": 9.9375,
+      "learning_rate": 3.5711729009001095e-06,
+      "loss": 0.1668,
+      "step": 110
+    },
+    {
+      "epoch": 0.5476190476190477,
+      "grad_norm": 10.125,
+      "learning_rate": 3.556873977446483e-06,
+      "loss": 0.1767,
+      "step": 115
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 8.0,
+      "learning_rate": 3.541696955766943e-06,
+      "loss": 0.1581,
+      "step": 120
+    },
+    {
+      "epoch": 0.5952380952380952,
+      "grad_norm": 10.1875,
+      "learning_rate": 3.5256524129747123e-06,
+      "loss": 0.1574,
+      "step": 125
+    },
+    {
+      "epoch": 0.6190476190476191,
+      "grad_norm": 11.3125,
+      "learning_rate": 3.5087515307725825e-06,
+      "loss": 0.186,
+      "step": 130
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 9.0,
+      "learning_rate": 3.4910060876602087e-06,
+      "loss": 0.1665,
+      "step": 135
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 8.875,
+      "learning_rate": 3.472428450725478e-06,
+      "loss": 0.1725,
+      "step": 140
+    },
+    {
+      "epoch": 0.6904761904761905,
+      "grad_norm": 10.125,
+      "learning_rate": 3.4530315670256834e-06,
+      "loss": 0.178,
+      "step": 145
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 9.4375,
+      "learning_rate": 3.432828954564515e-06,
+      "loss": 0.1679,
+      "step": 150
+    },
+    {
+      "epoch": 0.7380952380952381,
+      "grad_norm": 9.375,
+      "learning_rate": 3.411834692871138e-06,
+      "loss": 0.1819,
+      "step": 155
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 9.9375,
+      "learning_rate": 3.390063413187941e-06,
+      "loss": 0.1764,
+      "step": 160
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 10.5,
+      "learning_rate": 3.3675302882737866e-06,
+      "loss": 0.1655,
+      "step": 165
+    },
+    {
+      "epoch": 0.8095238095238095,
+      "grad_norm": 10.0,
+      "learning_rate": 3.344251021829867e-06,
+      "loss": 0.1759,
+      "step": 170
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 8.375,
+      "learning_rate": 3.3202418375555435e-06,
+      "loss": 0.1502,
+      "step": 175
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 10.6875,
+      "learning_rate": 3.29551946784178e-06,
+      "loss": 0.1667,
+      "step": 180
+    },
+    {
+      "epoch": 0.8809523809523809,
+      "grad_norm": 9.375,
+      "learning_rate": 3.2701011421100723e-06,
+      "loss": 0.1684,
+      "step": 185
+    },
+    {
+      "epoch": 0.9047619047619048,
+      "grad_norm": 7.875,
+      "learning_rate": 3.2440045748049846e-06,
+      "loss": 0.1475,
+      "step": 190
+    },
+    {
+      "epoch": 0.9285714285714286,
+      "grad_norm": 9.4375,
+      "learning_rate": 3.217247953048661e-06,
+      "loss": 0.1741,
+      "step": 195
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 9.5625,
+      "learning_rate": 3.1898499239659283e-06,
+      "loss": 0.1498,
+      "step": 200
+    },
+    {
+      "epoch": 0.9761904761904762,
+      "grad_norm": 9.3125,
+      "learning_rate": 3.1618295816888093e-06,
+      "loss": 0.1632,
+      "step": 205
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 9.0625,
+      "learning_rate": 3.133206454049512e-06,
+      "loss": 0.1533,
+      "step": 210
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.1544312834739685,
+      "eval_runtime": 1.7978,
+      "eval_samples_per_second": 18.912,
+      "eval_steps_per_second": 9.456,
+      "step": 210
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 630,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0275582854792479e+18,
+  "train_batch_size": 28,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a77b4ae7804fa9c8fd0ea5f5b412572769cfd2d7b416be575188d539737ba83
+size 5688