Training in progress, step 500

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 50257
+}

config.json

@@ -10,22 +10,22 @@
   "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
-    }
-  },
-  "vocab_size": 50257
-}
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "vocab_size": 50258
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abf846756a6508565d1a7876858dffb399a944ca7624719e4632c794d89652b6
+size 497777280

runs/Jul21_05-40-25_c7096466ca2f/events.out.tfevents.1721540478.c7096466ca2f.2896.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e13aa5a0444227d8aa2f18c95dc5db3bcb66a0f4e24f51075a631bff99a5acf
+size 4831

runs/Jul21_05-42-37_c7096466ca2f/events.out.tfevents.1721540580.c7096466ca2f.3474.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9ec88ad4a01161b64a1102bb5b75bd46dd30622eec752f59ff3060fdcb886b5
+size 4831

runs/Jul21_05-43-41_c7096466ca2f/events.out.tfevents.1721540628.c7096466ca2f.3775.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc945c6b026497a0a2e71436dd724412fce80a274813e64d47a57ccb3a8a8f31
+size 5042

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer.json

@@ -2,7 +2,17 @@
   "version": "1.0",
   "truncation": null,
   "padding": null,
-  "added_tokens": [],
+  "added_tokens": [
+    {
+      "id": 50257,
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
   "normalizer": null,
   "pre_tokenizer": {
     "type": "ByteLevel",

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff315b4c90ce830c7a6334e22b3a9253c2c588d1f62f9aa4fff39966c5a17d46
+size 5176