Training in progress, step 500

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": 40,
+  "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": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 20000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15db108f38c7c01995f2722bec833e44822ece006282cd6fe23ac03fdf721fdb
+size 404824704

runs/Jun19_01-29-31_7feeb9603531/events.out.tfevents.1718760575.7feeb9603531.340.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38f53eb54cf7fc389a9201c46ed49fa99c64d8c51533788d0fd040c57cee5446
+size 5184

runs/Jun19_02-41-36_7feeb9603531/events.out.tfevents.1718764901.7feeb9603531.340.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8bf9410ded2ea3d7022059b5ffa78bcd611b734e84246257369824026672fb6
+size 5184

runs/Jun19_02-41-53_7feeb9603531/events.out.tfevents.1718764918.7feeb9603531.340.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ae6a821d72acd011dc0fd22d663791b801c150f122aac04eaf72a0b0ebb7198
+size 5184

runs/Jun19_02-51-42_7feeb9603531/events.out.tfevents.1718765507.7feeb9603531.76733.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd10a75ef04e4e7c89ba8f0593bd5989254820e6fad4059781a8fdd08bddaceb
+size 5121

runs/Jun19_02-53-41_7feeb9603531/events.out.tfevents.1718765627.7feeb9603531.76733.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5841492d837d6edf4228b7d315d8e014d7cded5b233f01936c566a62d4960e79
+size 15610

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 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85457f8b1e3b79673ea0b63161a631ba74633c26b033f0ab4451933e78df7bdb
+size 5176