Training in progress, step 5000

.gitignore

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

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 128,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "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": 50000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5dbec9dca781698d9cc6ca4643b02c408f89e6efd0a4a3faae43873c7eb9962
+size 509608509

runs/May29_03-17-56_a08b859d3365/1685330281.8900332/events.out.tfevents.1685330281.a08b859d3365.1794.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:745cd12421b1134a6e4576df8746f9ec2949149c782c6c8aa37fccf1d8c9755a
+size 5889

runs/May29_03-17-56_a08b859d3365/events.out.tfevents.1685330281.a08b859d3365.1794.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94054ccbf58314f76adf8616d029121e584f16cd8f397d650bafc956fdad3c87
+size 4668

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 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "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:a14f199303042b9754081df6a7175fd97f16aa4fea67b39c69932be2735411dc
+size 3579