Training in progress, epoch 0

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

added_tokens.json

@@ -0,0 +1,45 @@
+{
+  "\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,
+  "<|PAD|>": 50299,
+  "<|assistant|>": 50296,
+  "<|end|>": 50298,
+  "<|system|>": 50295,
+  "<|user|>": 50297
+}

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "Salesforce/codegen-350M-mono",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "CodeGenForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "codegen",
+  "n_ctx": 2048,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 20,
+  "n_positions": 2048,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 32,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "temperature": 1.0
+    }
+  },
+  "tie_word_embeddings": false,
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 50300
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89893e9ec293142f9bd4b30110d8ea4e31a145d273e6f39d3555bf84af9e608f
+size 1503420337

runs/Jul02_05-43-38_4f5b6a9b3ebc/events.out.tfevents.1688276629.4f5b6a9b3ebc.170.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7c7ccdc14c9f6474d4a497f17b2f7c3db7f687c9974df36cb0c3ddad428f898
+size 4184

runs/Jul02_05-45-34_4f5b6a9b3ebc/events.out.tfevents.1688276737.4f5b6a9b3ebc.4515.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28be5a42377367570bc2c68c92884e175f4b78c18c7bb5f0730de4aedb179c43
+size 4541

runs/Jul02_05-51-27_4f5b6a9b3ebc/events.out.tfevents.1688277090.4f5b6a9b3ebc.6149.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:268ccf7035b964bbc575727e665c87dc631b006afd2d7510221450afd8b45f1c
+size 4540

runs/Jul02_05-56-25_4f5b6a9b3ebc/events.out.tfevents.1688277388.4f5b6a9b3ebc.7498.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a72d681c0dd557337f4c8af26cd4a93b18d70ff3b8da0fb19242db8e6ef3885b
+size 7052

special_tokens_map.json

@@ -0,0 +1,13 @@
+{
+  "additional_special_tokens": [
+    "<|system|>",
+    "<|assistant|>",
+    "<|user|>",
+    "<|end|>",
+    "<|PAD|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|PAD|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "additional_special_tokens": [
+    "<|system|>",
+    "<|assistant|>",
+    "<|user|>",
+    "<|end|>",
+    "<|PAD|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1400,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91917d9d6905e2d1a2b5bd71d9fffe5c19986d83cae7f588798637df0a4f0a50
+size 4091