Training in progress, step 500

config.json

@@ -1,14 +1,39 @@
 {
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
   "architectures": [
-    "LangModel"
+    "GPT2LMHeadModel"
   ],
-  "d_hid": 200,
-  "dropout": 0.2,
-  "emsize": 200,
-  "model_type": "langmodel",
-  "nhead": 2,
-  "nlayers": 2,
-  "ntokens": 25000,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 128,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 3,
+  "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"
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 25001
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eebd2af352ffd5399c7425ed2204b014a862c3d52a12ca01d94a49397c22d68
-size 46039288
+oid sha256:c924a5f9c8bb9dda86642e70af8ec1b5a14e06b98a868ff1cf4cb27c2c28183b
+size 165013384

runs/Jun03_13-42-21_ip-10-192-11-152/events.out.tfevents.1717422142.ip-10-192-11-152.3529.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c290e5324c06f0a8980c24c8138c8d48f8e4c90362eb1eec055451da295ed47
+size 5510

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0642b16b2116e366c71c10493504121648350056232f2926cae8fcf6c95bda74
+oid sha256:ac87c4a3c2f42de6c85707a88269de7e5ec40ca6c1e52f5916c1848b0b136dcd
 size 5112