Training in progress, step 500

added_tokens.json

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

config.json

@@ -1,31 +1,31 @@
-{
-    "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_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,
-    "torch_dtype": "float32",
-    "transformers_version": "4.42.4",
-    "use_cache": true,
-    "vocab_size": 50258
-}
+{
+  "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_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "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,
+  "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:a7b4b3a36ccb72320f06f811b5086b0dffef368398d1dfd3ddf508543ed5e407
+size 327661000

runs/Jul22_23-21-18_e063f4f30784/events.out.tfevents.1721690539.e063f4f30784.915.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c94c0827a138b5b639a9bc08aaf2f5a9c0295f568b42451c9ce5672a439a18d
+size 5047

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:df96aeb76f7e146e0bb1493dc619ceee3faf920acc643f3711f00a5ef241ee41
+size 5176