Training in progress, step 75

config.json

@@ -1,27 +1,39 @@
 {
-  "_name_or_path": "distilroberta-base",
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
   "architectures": [
-    "RobertaForMaskedLM"
+    "GPT2LMHeadModel"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 6,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "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": "4.46.3",
-  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 50257
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68c43d8450410e54be957dacbebe12294c0edd506f4c26325cb7a69d955b800d
-size 328693404
+oid sha256:d07042e855324db274cb1729e6d34ec16efbe1fd9ecb5c56e105e6cea4eebc0e
+size 497774208

runs/Dec05_17-37-24_xtaco/events.out.tfevents.1733449082.xtaco.8356.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b5d283c532d1d36f0d6dcc642e45e0d8de91b2c2ca8ef2a739be0816e48d6ef
+size 5333

runs/Dec05_17-40-38_xtaco/events.out.tfevents.1733449240.xtaco.8356.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f7b87f643de8562614a7b68bdc5bb7706ec7be87668de23c735a8ed77fde3c6
+size 5333

runs/Dec05_17-41-18_xtaco/events.out.tfevents.1733449279.xtaco.8356.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91317a65fd2160d76338e23a74d84d383b1fb37590976293e1f6bae8163fb9a1
+size 5333

runs/Dec05_17-46-25_xtaco/events.out.tfevents.1733449585.xtaco.8356.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96e4ccf91f7ec0d411d77363b264c662f17a09f4679c9af9c2fbd97c129b0234
+size 5333

runs/Dec05_17-47-24_xtaco/events.out.tfevents.1733449645.xtaco.8356.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7795d12ae4fa932e81bb42a7dc3494a369123fa39c053c474f080d1bd37a4805
+size 7011

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07ad1afd081a2d1b0c3592a38e466d6d76856dd6d77038b546e9cfd2df72ace6
+oid sha256:93b1bfa9930fb3ccd5b9a77d266f87599e833eb031ea1f015d4f7379162915e0
 size 4847