Training in progress, step 16696

added_tokens.json

@@ -0,0 +1,42 @@
+{
+  "\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,
+  "<|im_end|>": 50295,
+  "<|im_start|>": 50296
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "microsoft/phi-1_5",
+  "activation_function": "gelu_new",
+  "architecture": {
+    "block_cls": "parallel",
+    "mixer": {},
+    "mlp": {
+      "mlp_cls": "mlp"
+    }
+  },
+  "architectures": [
+    "MixFormerSequentialForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "microsoft/phi-1_5--configuration_mixformer_sequential.MixFormerSequentialConfig",
+    "AutoModelForCausalLM": "microsoft/phi-1_5--modeling_mixformer_sequential.MixFormerSequentialForCausalLM"
+  },
+  "embd_layer": "default",
+  "embd_pdrop": 0.0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "mixformer-sequential",
+  "n_embd": 2048,
+  "n_head": 32,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 2048,
+  "phyagi_version": "0.0.4.dev",
+  "resid_pdrop": 0.0,
+  "rotary_dim": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0.dev0",
+  "use_cache": false,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.34.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:effd48f0e066c9b220d521a1e1dbddcf6118c8aabf6d34fb14a1a4a0681d42b5
+size 2829283393

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c942cd25743b097388d352ade11d35966dbb891f7652b861d1c290c164bd6445
+size 5755