Training in progress, step 1

.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": null,
+  "embd_pdrop": 0.1,
+  "eos_token_id": null,
+  "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": "4.25.1",
+  "use_cache": true,
+  "vocab_size": 49442
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a754531652c50de1d2c83f9a36165952ddcfb1d52612a26d09469310afa9410
+size 507894333

runs/Dec20_19-34-21_caffaf8c0f33/1671564881.7859092/events.out.tfevents.1671564881.caffaf8c0f33.409.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ebd151b49bc88fc3fff0c3df55dc62714146364c953c38d34ab5ea188be827a
+size 5488

runs/Dec20_19-34-21_caffaf8c0f33/events.out.tfevents.1671564881.caffaf8c0f33.409.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa36ac29b86fbdb290b4244b31e4335155877fcd63ff6af7b1be1db3b2ffb6cd
+size 3930

runs/Dec20_19-36-14_caffaf8c0f33/1671564988.0554037/events.out.tfevents.1671564988.caffaf8c0f33.409.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34eb53cb172e92f455823956bb91359209229a866bbacb64b7cd87259ce0c6e5
+size 5488

runs/Dec20_19-36-14_caffaf8c0f33/events.out.tfevents.1671564988.caffaf8c0f33.409.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a085cda5ea2b56f0368858800330deafb57b7552d67b696deae0f5866396803d
+size 4350

runs/Dec20_19-41-52_caffaf8c0f33/1671565355.0092053/events.out.tfevents.1671565355.caffaf8c0f33.409.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:542e80dded3048bf2f53a865391ab570beec532dad22da82304a15860dbea112
+size 5488

runs/Dec20_19-41-52_caffaf8c0f33/events.out.tfevents.1671565355.caffaf8c0f33.409.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eee248457b380aa172e12863fbc6bbc386264b16a07a095c57bca2af0a07ad31
+size 4378

special_tokens_map.json

@@ -0,0 +1,3 @@
+{
+  "pad_token": "[PAD]"
+}

tokenizer_config.json

@@ -0,0 +1,4 @@
+{
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a791ee764bde380b047f9e53c16d570d99becf91fe2a521403a3b553ab81ef7c
+size 3387