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": 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": "4.40.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c21d44ef47507672827fa8f2b09650285a296322ca17cef71d0a8468beab4eaa
+size 497774208

runs/May13_04-00-55_e40509a4fa82/events.out.tfevents.1715572856.e40509a4fa82.2039.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c151c079cec0049cacbd36ed3dc54b3884e66e714199eb77df02ec9867e5ce82
+size 4184

runs/May13_04-02-02_e40509a4fa82/events.out.tfevents.1715572932.e40509a4fa82.2831.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:921fcb408276ae7f48b3108d719daa6fc6434caa48a82743c9e6abb1de39ee5b
+size 4184

runs/May13_04-02-40_e40509a4fa82/events.out.tfevents.1715572961.e40509a4fa82.2831.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35e34899fce96a23f6137731f931a9431584f06d57ac61aa88475e12dab1bd83
+size 4184

runs/May13_04-03-33_e40509a4fa82/events.out.tfevents.1715573015.e40509a4fa82.3208.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8255c7cfb653848bc7ae01b373d5cdf5483522b248b7ce22fd7b08329bd38cd
+size 5384

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcfe34a4c4ce9d46e7ec53b9c7259ca8f127c04a2d59e11272b41e6edb408766
+size 5048