Training in progress, step 500

config.json

@@ -0,0 +1,32 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.15,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.15,
+  "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,
+  "pad_token_id": 50256,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.15,
+  "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": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bf76e8b0ed3752337409b0f4f43d0bafda39aa83d86415cf9114a96e67c2ea4
+size 497774208

runs/Jan07_09-23-22_ce6ec11cf6b1/events.out.tfevents.1704621968.ce6ec11cf6b1.1005.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6a4e5fb22c4f37bc3f5f907c7c6983e007b918147001cbb6817c7c256e27165
+size 4422

runs/Jan07_10-09-11_ce6ec11cf6b1/events.out.tfevents.1704622196.ce6ec11cf6b1.12914.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44830df7ab4dcbad135b2ca0de9221d9494eb7c1d5614cb3df17acf7997f08c8
+size 4421

runs/Jan07_10-11-11_ce6ec11cf6b1/events.out.tfevents.1704622321.ce6ec11cf6b1.13493.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81de403afa8d024bbf1d3e3f45452179ae7c10655233e1722160ed602d59945f
+size 4578

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 sha256:7ac1ebb8de4446b5ed80ecc9fdb951d0c8120336f8feea073c04aab852056087
+size 4664