Training in progress, epoch 1

.gitignore

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

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2ForSequenceClassification"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3,
+    "4": 4,
+    "5": 5,
+    "6": 6,
+    "7": 7,
+    "8": 8,
+    "9": 9,
+    "10": 10,
+    "11": 11,
+    "12": 12,
+    "13": 13,
+    "14": 14
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3,
+    "4": 4,
+    "5": 5,
+    "6": 6,
+    "7": 7,
+    "8": 8,
+    "9": 9,
+    "10": 10,
+    "11": 11,
+    "12": 12,
+    "13": 13,
+    "14": 14
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 50256,
+  "problem_type": "single_label_classification",
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b284694712264e772a7f23a087bd6b7a70287538d752dea14d24b1741ee20c94
+size 510444289

runs/Sep14_06-48-57_8ca0127a940c/1694674147.2173374/events.out.tfevents.1694674147.8ca0127a940c.203.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a158974a8945ca9b178826203ba40fa542f81011f5f58641bbff436a7b4152b
+size 5855

runs/Sep14_06-48-57_8ca0127a940c/events.out.tfevents.1694674147.8ca0127a940c.203.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ba67d3daa489290585a1a6c7b1712d888d2dd820a08d4e9cf26fc5a1b1bc421
+size 4634

runs/Sep14_06-49-48_8ca0127a940c/1694674191.829211/events.out.tfevents.1694674191.8ca0127a940c.203.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b4dd7d599605c7a79729d1b59762895f8361b803ae0bc21166c5566e1d0b416
+size 5855

runs/Sep14_06-49-48_8ca0127a940c/events.out.tfevents.1694674191.8ca0127a940c.203.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13ff9c91158e0af346f8c48766cdba83b27c14266d2f0f961afa478274ad8f42
+size 4634

runs/Sep14_06-50-51_8ca0127a940c/1694674254.3778038/events.out.tfevents.1694674254.8ca0127a940c.203.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6caf2b534be3a255fa8b945f70fb8b6a361a2db6caf4f28ab1c06dc805a96e12
+size 5855

runs/Sep14_06-50-51_8ca0127a940c/events.out.tfevents.1694674254.8ca0127a940c.203.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f553845320c7a3689d88d5b725b91a01033208b53f2165779915580f431820ac
+size 5392

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71088f1780c51e5e48acabdd21ea7617679d764080cfa465ad0c8ef28f7fc69b
+size 3579