Upload task output a0b6e564-b8fd-4183-aee5-1faf9aaeb03b

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

config.json

@@ -0,0 +1,138 @@
+{
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "model_type": "phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1.0700000524520874,
+      1.1200000047683716,
+      1.149999976158142,
+      1.4199999570846558,
+      1.5699999332427979,
+      1.7999999523162842,
+      2.129999876022339,
+      2.129999876022339,
+      3.009999990463257,
+      5.910000324249268,
+      6.950000286102295,
+      9.070000648498535,
+      9.930000305175781,
+      10.710000038146973,
+      11.130000114440918,
+      14.609999656677246,
+      15.409998893737793,
+      19.809999465942383,
+      37.279998779296875,
+      38.279998779296875,
+      38.599998474121094,
+      40.12000274658203,
+      46.20000457763672,
+      50.940006256103516,
+      53.66000747680664,
+      54.9373893737793,
+      56.89738845825195,
+      57.28738784790039,
+      59.98738479614258,
+      60.86738586425781,
+      60.887386322021484,
+      61.71739196777344,
+      62.91739273071289,
+      62.957393646240234,
+      63.41739273071289,
+      63.8173942565918,
+      63.83739471435547,
+      63.897396087646484,
+      63.93739700317383,
+      64.06739807128906,
+      64.11434936523438,
+      64.12435150146484,
+      64.15435028076172,
+      64.19435119628906,
+      64.24435424804688,
+      64.57435607910156,
+      64.69000244140625,
+      64.76000213623047
+    ],
+    "short_factor": [
+      1.1,
+      1.1,
+      1.1,
+      1.3000000000000003,
+      1.3500000000000003,
+      1.3500000000000003,
+      1.4000000000000004,
+      1.5500000000000005,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.000000000000001,
+      2.0500000000000007,
+      2.0500000000000007,
+      2.0500000000000007,
+      2.0500000000000007,
+      2.0500000000000007,
+      2.0500000000000007,
+      2.1000000000000005,
+      2.1000000000000005,
+      2.1500000000000004,
+      2.25,
+      2.25,
+      2.25,
+      2.25,
+      2.25,
+      2.3999999999999995,
+      2.4499999999999993,
+      2.499999999999999,
+      2.6999999999999984,
+      2.6999999999999984,
+      2.7499999999999982,
+      2.799999999999998,
+      2.8999999999999977,
+      3.049999999999997
+    ],
+    "type": "longrope"
+  },
+  "rope_theta": 10000.0,
+  "sliding_window": 262144,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "vocab_size": 32064
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    32000,
+    32001,
+    32007
+  ],
+  "pad_token_id": 32000,
+  "transformers_version": "4.51.3"
+}

loss.txt

@@ -0,0 +1 @@
+420,1.7710609436035156

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86295e2c06b4c536425da596a3d422a69ea92612f6a63e2b7f47968f3421c61e
+size 4972489328

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9b5392e70f2c83136b42a07215ff64ccbf96734e8cd0f27e0e959c42a3c99d2
+size 2669692552

model.safetensors.index.json

@@ -0,0 +1,202 @@
+{
+  "metadata": {
+    "total_size": 7642159104
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "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 +1,132 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,646 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 420,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03571428571428571,
+      "grad_norm": 8.5625,
+      "learning_rate": 1.4469972592918759e-06,
+      "loss": 2.4755,
+      "step": 5
+    },
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 8.25,
+      "learning_rate": 3.2557438334067203e-06,
+      "loss": 2.5363,
+      "step": 10
+    },
+    {
+      "epoch": 0.10714285714285714,
+      "grad_norm": 7.71875,
+      "learning_rate": 5.064490407521566e-06,
+      "loss": 2.4113,
+      "step": 15
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 7.03125,
+      "learning_rate": 6.87323698163641e-06,
+      "loss": 2.4006,
+      "step": 20
+    },
+    {
+      "epoch": 0.17857142857142858,
+      "grad_norm": 6.03125,
+      "learning_rate": 8.681983555751255e-06,
+      "loss": 2.3508,
+      "step": 25
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 5.6875,
+      "learning_rate": 1.04907301298661e-05,
+      "loss": 2.2081,
+      "step": 30
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 4.875,
+      "learning_rate": 1.2299476703980945e-05,
+      "loss": 2.1214,
+      "step": 35
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 3.875,
+      "learning_rate": 1.2658191303243417e-05,
+      "loss": 1.9663,
+      "step": 40
+    },
+    {
+      "epoch": 0.32142857142857145,
+      "grad_norm": 2.9375,
+      "learning_rate": 1.264586831164522e-05,
+      "loss": 1.8873,
+      "step": 45
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 3.28125,
+      "learning_rate": 1.262408786890284e-05,
+      "loss": 1.8287,
+      "step": 50
+    },
+    {
+      "epoch": 0.39285714285714285,
+      "grad_norm": 2.375,
+      "learning_rate": 1.2592886226413729e-05,
+      "loss": 1.8521,
+      "step": 55
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 2.375,
+      "learning_rate": 1.2552315316232544e-05,
+      "loss": 1.778,
+      "step": 60
+    },
+    {
+      "epoch": 0.4642857142857143,
+      "grad_norm": 2.25,
+      "learning_rate": 1.250244266463537e-05,
+      "loss": 1.7535,
+      "step": 65
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.328125,
+      "learning_rate": 1.2443351279728905e-05,
+      "loss": 1.7633,
+      "step": 70
+    },
+    {
+      "epoch": 0.5357142857142857,
+      "grad_norm": 2.359375,
+      "learning_rate": 1.2375139513291645e-05,
+      "loss": 1.7053,
+      "step": 75
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 2.28125,
+      "learning_rate": 1.2297920897077063e-05,
+      "loss": 1.7079,
+      "step": 80
+    },
+    {
+      "epoch": 0.6071428571428571,
+      "grad_norm": 2.671875,
+      "learning_rate": 1.2211823953851207e-05,
+      "loss": 1.7254,
+      "step": 85
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.2116991983479236e-05,
+      "loss": 1.6896,
+      "step": 90
+    },
+    {
+      "epoch": 0.6785714285714286,
+      "grad_norm": 2.25,
+      "learning_rate": 1.2013582824416955e-05,
+      "loss": 1.7449,
+      "step": 95
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 2.234375,
+      "learning_rate": 1.1901768591004251e-05,
+      "loss": 1.7294,
+      "step": 100
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 2.28125,
+      "learning_rate": 1.1781735386997792e-05,
+      "loss": 1.7083,
+      "step": 105
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 2.28125,
+      "learning_rate": 1.1653682995819667e-05,
+      "loss": 1.6826,
+      "step": 110
+    },
+    {
+      "epoch": 0.8214285714285714,
+      "grad_norm": 2.40625,
+      "learning_rate": 1.151782454803761e-05,
+      "loss": 1.7017,
+      "step": 115
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 2.375,
+      "learning_rate": 1.1374386166630197e-05,
+      "loss": 1.7088,
+      "step": 120
+    },
+    {
+      "epoch": 0.8928571428571429,
+      "grad_norm": 2.375,
+      "learning_rate": 1.1223606590627465e-05,
+      "loss": 1.6843,
+      "step": 125
+    },
+    {
+      "epoch": 0.9285714285714286,
+      "grad_norm": 2.203125,
+      "learning_rate": 1.106573677775336e-05,
+      "loss": 1.7198,
+      "step": 130
+    },
+    {
+      "epoch": 0.9642857142857143,
+      "grad_norm": 2.390625,
+      "learning_rate": 1.0901039486731374e-05,
+      "loss": 1.7226,
+      "step": 135
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.3125,
+      "learning_rate": 1.0729788839948573e-05,
+      "loss": 1.7045,
+      "step": 140
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.788003921508789,
+      "eval_runtime": 0.4159,
+      "eval_samples_per_second": 9.618,
+      "eval_steps_per_second": 9.618,
+      "step": 140
+    },
+    {
+      "epoch": 1.0357142857142858,
+      "grad_norm": 2.171875,
+      "learning_rate": 1.055226986720594e-05,
+      "loss": 1.6442,
+      "step": 145
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": 2.109375,
+      "learning_rate": 1.0368778031314411e-05,
+      "loss": 1.6284,
+      "step": 150
+    },
+    {
+      "epoch": 1.1071428571428572,
+      "grad_norm": 2.3125,
+      "learning_rate": 1.017961873632617e-05,
+      "loss": 1.6747,
+      "step": 155
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 2.125,
+      "learning_rate": 9.98510681921975e-06,
+      "loss": 1.6428,
+      "step": 160
+    },
+    {
+      "epoch": 1.1785714285714286,
+      "grad_norm": 2.21875,
+      "learning_rate": 9.785566025884956e-06,
+      "loss": 1.6027,
+      "step": 165
+    },
+    {
+      "epoch": 1.2142857142857142,
+      "grad_norm": 2.359375,
+      "learning_rate": 9.58132847227978e-06,
+      "loss": 1.6244,
+      "step": 170
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 2.203125,
+      "learning_rate": 9.372734091656167e-06,
+      "loss": 1.6336,
+      "step": 175
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 2.171875,
+      "learning_rate": 9.160130068774655e-06,
+      "loss": 1.6574,
+      "step": 180
+    },
+    {
+      "epoch": 1.3214285714285714,
+      "grad_norm": 2.25,
+      "learning_rate": 8.943870262049619e-06,
+      "loss": 1.6429,
+      "step": 185
+    },
+    {
+      "epoch": 1.3571428571428572,
+      "grad_norm": 2.25,
+      "learning_rate": 8.724314614586853e-06,
+      "loss": 1.6529,
+      "step": 190
+    },
+    {
+      "epoch": 1.3928571428571428,
+      "grad_norm": 2.34375,
+      "learning_rate": 8.501828555093793e-06,
+      "loss": 1.6533,
+      "step": 195
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 1.96875,
+      "learning_rate": 8.276782389659505e-06,
+      "loss": 1.6222,
+      "step": 200
+    },
+    {
+      "epoch": 1.4642857142857144,
+      "grad_norm": 2.125,
+      "learning_rate": 8.049550685416733e-06,
+      "loss": 1.6329,
+      "step": 205
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 2.078125,
+      "learning_rate": 7.820511647111883e-06,
+      "loss": 1.5851,
+      "step": 210
+    },
+    {
+      "epoch": 1.5357142857142856,
+      "grad_norm": 2.25,
+      "learning_rate": 7.590046487620542e-06,
+      "loss": 1.6258,
+      "step": 215
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 2.3125,
+      "learning_rate": 7.358538793456268e-06,
+      "loss": 1.6677,
+      "step": 220
+    },
+    {
+      "epoch": 1.6071428571428572,
+      "grad_norm": 2.21875,
+      "learning_rate": 7.126373886328697e-06,
+      "loss": 1.6719,
+      "step": 225
+    },
+    {
+      "epoch": 1.6428571428571428,
+      "grad_norm": 2.3125,
+      "learning_rate": 6.893938181813584e-06,
+      "loss": 1.6586,
+      "step": 230
+    },
+    {
+      "epoch": 1.6785714285714286,
+      "grad_norm": 2.09375,
+      "learning_rate": 6.6616185462022054e-06,
+      "loss": 1.6291,
+      "step": 235
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 2.265625,
+      "learning_rate": 6.429801652600605e-06,
+      "loss": 1.6306,
+      "step": 240
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 2.125,
+      "learning_rate": 6.19887333735037e-06,
+      "loss": 1.6716,
+      "step": 245
+    },
+    {
+      "epoch": 1.7857142857142856,
+      "grad_norm": 2.078125,
+      "learning_rate": 5.9692179578421085e-06,
+      "loss": 1.6072,
+      "step": 250
+    },
+    {
+      "epoch": 1.8214285714285714,
+      "grad_norm": 2.546875,
+      "learning_rate": 5.741217752790515e-06,
+      "loss": 1.5944,
+      "step": 255
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 2.078125,
+      "learning_rate": 5.515252206035749e-06,
+      "loss": 1.6246,
+      "step": 260
+    },
+    {
+      "epoch": 1.8928571428571428,
+      "grad_norm": 2.25,
+      "learning_rate": 5.291697414930032e-06,
+      "loss": 1.6281,
+      "step": 265
+    },
+    {
+      "epoch": 1.9285714285714286,
+      "grad_norm": 2.453125,
+      "learning_rate": 5.0709254643607234e-06,
+      "loss": 1.6561,
+      "step": 270
+    },
+    {
+      "epoch": 1.9642857142857144,
+      "grad_norm": 2.203125,
+      "learning_rate": 4.853303807451746e-06,
+      "loss": 1.6419,
+      "step": 275
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.0625,
+      "learning_rate": 4.6391946539741255e-06,
+      "loss": 1.6224,
+      "step": 280
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.771442174911499,
+      "eval_runtime": 0.2948,
+      "eval_samples_per_second": 13.568,
+      "eval_steps_per_second": 13.568,
+      "step": 280
+    },
+    {
+      "epoch": 2.0357142857142856,
+      "grad_norm": 2.203125,
+      "learning_rate": 4.428954367483572e-06,
+      "loss": 1.6102,
+      "step": 285
+    },
+    {
+      "epoch": 2.0714285714285716,
+      "grad_norm": 2.109375,
+      "learning_rate": 4.222932872188511e-06,
+      "loss": 1.5871,
+      "step": 290
+    },
+    {
+      "epoch": 2.107142857142857,
+      "grad_norm": 2.046875,
+      "learning_rate": 4.021473070535769e-06,
+      "loss": 1.6075,
+      "step": 295
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 2.265625,
+      "learning_rate": 3.8249102724833e-06,
+      "loss": 1.6176,
+      "step": 300
+    },
+    {
+      "epoch": 2.1785714285714284,
+      "grad_norm": 2.1875,
+      "learning_rate": 3.633571637409841e-06,
+      "loss": 1.6132,
+      "step": 305
+    },
+    {
+      "epoch": 2.2142857142857144,
+      "grad_norm": 2.0625,
+      "learning_rate": 3.447775629590425e-06,
+      "loss": 1.6448,
+      "step": 310
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 2.046875,
+      "learning_rate": 3.2678314881440106e-06,
+      "loss": 1.568,
+      "step": 315
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 2.1875,
+      "learning_rate": 3.094038712335502e-06,
+      "loss": 1.6433,
+      "step": 320
+    },
+    {
+      "epoch": 2.3214285714285716,
+      "grad_norm": 2.234375,
+      "learning_rate": 2.9266865630887656e-06,
+      "loss": 1.5936,
+      "step": 325
+    },
+    {
+      "epoch": 2.357142857142857,
+      "grad_norm": 2.515625,
+      "learning_rate": 2.7660535815403792e-06,
+      "loss": 1.6269,
+      "step": 330
+    },
+    {
+      "epoch": 2.392857142857143,
+      "grad_norm": 2.171875,
+      "learning_rate": 2.612407125435396e-06,
+      "loss": 1.6385,
+      "step": 335
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 2.453125,
+      "learning_rate": 2.4660029241367617e-06,
+      "loss": 1.5861,
+      "step": 340
+    },
+    {
+      "epoch": 2.4642857142857144,
+      "grad_norm": 2.484375,
+      "learning_rate": 2.327084652989029e-06,
+      "loss": 1.6108,
+      "step": 345
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 2.15625,
+      "learning_rate": 2.1958835277447983e-06,
+      "loss": 1.591,
+      "step": 350
+    },
+    {
+      "epoch": 2.5357142857142856,
+      "grad_norm": 2.109375,
+      "learning_rate": 2.0726179197289025e-06,
+      "loss": 1.5913,
+      "step": 355
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 2.078125,
+      "learning_rate": 1.9574929923809093e-06,
+      "loss": 1.6041,
+      "step": 360
+    },
+    {
+      "epoch": 2.607142857142857,
+      "grad_norm": 2.078125,
+      "learning_rate": 1.8507003597808046e-06,
+      "loss": 1.6216,
+      "step": 365
+    },
+    {
+      "epoch": 2.642857142857143,
+      "grad_norm": 2.28125,
+      "learning_rate": 1.7524177677262752e-06,
+      "loss": 1.581,
+      "step": 370
+    },
+    {
+      "epoch": 2.678571428571429,
+      "grad_norm": 2.25,
+      "learning_rate": 1.6628087978923687e-06,
+      "loss": 1.6039,
+      "step": 375
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 2.28125,
+      "learning_rate": 1.5820225955659404e-06,
+      "loss": 1.6316,
+      "step": 380
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 2.296875,
+      "learning_rate": 1.5101936214080384e-06,
+      "loss": 1.5491,
+      "step": 385
+    },
+    {
+      "epoch": 2.7857142857142856,
+      "grad_norm": 2.15625,
+      "learning_rate": 1.4474414276574078e-06,
+      "loss": 1.6135,
+      "step": 390
+    },
+    {
+      "epoch": 2.821428571428571,
+      "grad_norm": 2.140625,
+      "learning_rate": 1.393870459147585e-06,
+      "loss": 1.6076,
+      "step": 395
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 2.109375,
+      "learning_rate": 1.3495698794687797e-06,
+      "loss": 1.6442,
+      "step": 400
+    },
+    {
+      "epoch": 2.892857142857143,
+      "grad_norm": 2.328125,
+      "learning_rate": 1.3146134225638807e-06,
+      "loss": 1.6241,
+      "step": 405
+    },
+    {
+      "epoch": 2.928571428571429,
+      "grad_norm": 2.046875,
+      "learning_rate": 1.2890592700055819e-06,
+      "loss": 1.614,
+      "step": 410
+    },
+    {
+      "epoch": 2.9642857142857144,
+      "grad_norm": 2.234375,
+      "learning_rate": 1.2729499541588994e-06,
+      "loss": 1.5876,
+      "step": 415
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.46875,
+      "learning_rate": 1.266312287390245e-06,
+      "loss": 1.6258,
+      "step": 420
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.7710609436035156,
+      "eval_runtime": 0.295,
+      "eval_samples_per_second": 13.558,
+      "eval_steps_per_second": 13.558,
+      "step": 420
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 420,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.221798892876595e+17,
+  "train_batch_size": 48,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:692eefe8141ab5dac88580e728e4790a63199904b70bffe1939aa3bd913a2235
+size 5816