Training in progress, step 1000

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": 8,
+  "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": "4.47.1",
+  "use_cache": true,
+  "vocab_size": 2052
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a0f24da74ea5e4886c49e00f02ec0e1d25214eba24a83eda661801a8c6febde
+size 236277584

runs/Jan29_10-41-06_7162016/events.out.tfevents.1738147275.7162016

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afa4f0d12f73553867793cfb5b27ab949f3ff4d83a3effb5bd17bc7c3c630e1e
+size 5463

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "BOS",
+  "eos_token": "EOS",
+  "pad_token": "PAD",
+  "unk_token": "UNK"
+}

tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "added_tokens_decoder": {
+    "2048": {
+      "content": "BOS",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2049": {
+      "content": "EOS",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2050": {
+      "content": "UNK",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2051": {
+      "content": "PAD",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "BOS",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "EOS",
+  "extra_special_tokens": {},
+  "model_max_length": 15,
+  "pad_token": "PAD",
+  "padding_side": "right",
+  "return_tensors": "pt",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "unk_token": "UNK"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f241f7911ddc3ccd87561a5ae12a9d9d64efb8c67a44f96cd50ddaaa32d3cd0d
+size 5304