Training in progress, epoch 0

added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "microsoft/phi-2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
+    "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
+  },
+  "embd_pdrop": 0.0,
+  "flash_attn": true,
+  "flash_rotary": true,
+  "fused_dense": true,
+  "img_processor": null,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "phi-msft",
+  "n_embd": 2560,
+  "n_head": 32,
+  "n_head_kv": null,
+  "n_inner": null,
+  "n_layer": 32,
+  "n_positions": 2048,
+  "resid_pdrop": 0.1,
+  "rotary_dim": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": false,
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.37.0.dev0"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88085fb4b2602024f93eb0806358293d851523e8fd7250b83c20e11c05bdac49
+size 4982539832

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:907200df5d2af505a3c03d62cdb52f7fbf6d7daec0087ec32d8e8b7c7a76b747
+size 839195995

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d4e3bb6b35b46751596430e926f90e93d9b135980b5278ae6c0d0a276184cb3
+size 2200426417

pytorch_model.bin.index.json

@@ -0,0 +1,332 @@
+{
+  "metadata": {
+    "total_size": 5821624320
+  },
+  "weight_map": {
+    "lm_head.linear.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_head.linear.weight": "pytorch_model-00002-of-00002.bin",
+    "lm_head.ln.bias": "pytorch_model-00002-of-00002.bin",
+    "lm_head.ln.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.embd.wte.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.25.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.26.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.27.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.28.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.29.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.mixer.Wqkv.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mixer.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mixer.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.ln.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.ln.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mixer.Wqkv.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mixer.Wqkv.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mixer.out_proj.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mixer.out_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.4.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.ln.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mixer.Wqkv.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mixer.Wqkv.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mixer.out_proj.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mixer.out_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

runs/Jan08_15-45-35_4872549ecd6c/events.out.tfevents.1704728736.4872549ecd6c.953.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25e71e536c83adbc0d4c7be760cb47b3c5c0011b42d9c0f142bf6098cbf52641
+size 22563

runs/Jan08_15-46-54_4872549ecd6c/events.out.tfevents.1704728815.4872549ecd6c.2947.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1963f9bc0351a3830fd866b616f0e4f585c358c59fbd7f011a0958faed1926e
+size 14625

runs/Jan08_16-15-00_4872549ecd6c/events.out.tfevents.1704730501.4872549ecd6c.3104.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80da90c3991284c5600141f54128a90a4e298d65037f6c739032e72279e33e99
+size 12198

runs/Jan08_16-20-25_4872549ecd6c/events.out.tfevents.1704730826.4872549ecd6c.5023.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af1f33e53eaf83bd9f5ae8bc399c4f0482839088067a55cd020e6e2be77cd50a
+size 4932

runs/Jan08_16-21-56_4872549ecd6c/events.out.tfevents.1704730917.4872549ecd6c.5106.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3651c219c767b5706f312c6238ed83fdc328aa09b6d765862f403298900d48da
+size 4932

runs/Jan08_16-24-59_4872549ecd6c/events.out.tfevents.1704731100.4872549ecd6c.5203.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd308d8f4e5f74f04758b95eb86e46aeaec1f307219950f343f3bf68d7afe26c
+size 34544

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "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": "<|endoftext|>",
+    "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 +1,324 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9445f0fafed7e959ce84626ddbf6fe543408f5a0de7a6359d99d5f0634ad3c74
+size 4795