Training in progress, step 500

.gitignore

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

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|EOS|>": 50257,
+  "<|pad|>": 50258
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "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,
+  "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": 50259
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5505363e9fa8f8c35e9831834750ba7ac068e5b7cf027908e18304f3706256dc
+size 510404157

runs/Jan08_06-22-58_a469b9e70b98/1673159004.5870433/events.out.tfevents.1673159004.a469b9e70b98.748.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e55167a2db918eb5f1d02a1357bc511b9cdadc4948ab2ac2b4002cf861ed1800
+size 5615

runs/Jan08_06-22-58_a469b9e70b98/1673159280.2435122/events.out.tfevents.1673159280.a469b9e70b98.748.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8825c921a9805f931d81a390be60ac30fbf575f079208d6f9095e7f9c69e4bb
+size 5615

runs/Jan08_06-22-58_a469b9e70b98/events.out.tfevents.1673159004.a469b9e70b98.748.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dd0e6c47690cd27d680e0fa62ba96c72d48ebe43cc420819e552f45ef7ca21f
+size 4223

runs/Jan08_06-22-58_a469b9e70b98/events.out.tfevents.1673159280.a469b9e70b98.748.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baf86a9638382af073f8aa159e42bce6453944548e1b1cbc2b0a5a0f160ec02a
+size 4494

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "gpt2",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a5c3b1c7626a0d6a18a73fa6824d9078e2f37927787ce460b9ade58a2f04719
+size 3515