Training in progress, step 100

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": 512,
+  "n_head": 8,
+  "n_inner": null,
+  "n_layer": 8,
+  "n_positions": 256,
+  "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": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56e79b96108cc0e585f33b7f6829c354e1cf5c78093c7e470a2b144aefeec262
+size 204340968

runs/Nov06_10-05-22_b7472b66d613/events.out.tfevents.1730887796.b7472b66d613.322.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ea625ba3486cec2c191b4e2179cc73228bc585fb3976286e5aa8c090f0dec94
+size 5624

runs/Nov06_10-10-31_b7472b66d613/events.out.tfevents.1730887887.b7472b66d613.322.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef4ef8e7818ae2806b16abcd218ff0c5492d252a99faf89a2178ecc079344fc1
+size 5611

runs/Nov06_10-12-01_b7472b66d613/events.out.tfevents.1730887941.b7472b66d613.322.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f63cb84916fb1b14651d3012d5cd5394df2a2335f47b71fda4f61dcac65fa818
+size 24783

runs/Nov06_10-15-06_b7472b66d613/events.out.tfevents.1730888111.b7472b66d613.322.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3907ed6c98f1f8cd59636d14440561e4e14342660dddc013e8a24e841db63da1
+size 7965

runs/Nov06_10-17-06_b7472b66d613/events.out.tfevents.1730888255.b7472b66d613.5665.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62fece14a38c6ba5e4f327b3829b2108dcf4108ca0d53c1e50e382fa27df584f
+size 10339

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": false,
+  "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 sha256:09108a4e4feea9a1d0509460284e7e06f331231524916e8b176ecba4b1a273ee
+size 5560