Training in progress, step 500

config.json

@@ -1,46 +1,27 @@
 {
-  "_name_or_path": "distilgpt2",
-  "_num_labels": 1,
-  "activation_function": "gelu_new",
+  "_name_or_path": "distilroberta-base",
   "architectures": [
-    "GPT2LMHeadModel"
+    "RobertaForMaskedLM"
   ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
-  "id2label": {
-    "0": "LABEL_0"
-  },
+  "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,
   "initializer_range": 0.02,
-  "label2id": {
-    "LABEL_0": 0
-  },
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
-  "n_inner": null,
-  "n_layer": 6,
-  "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
-    }
-  },
+  "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",
   "torch_dtype": "float32",
   "transformers_version": "4.40.0.dev0",
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 50257
+  "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d545c9f0a3d32e887c2b7ff51860170dece08504805e4e4b8d65eb9e44b1464
-size 327657928
+oid sha256:e5db9f3c64a32ad6d173f92673c2dfb0866581477e6f64ee6c5e29152513d27d
+size 328693404

runs/Apr07_06-17-03_DESKTOP-RHJ1ESI/events.out.tfevents.1712441824.DESKTOP-RHJ1ESI.222551.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:869511f8c4bb6c0df550041c77ae0baaca45d7d145ca73db48dc9bf8a02f0727
+size 4978

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dc9f4e890c451ebdca6020070675b7be4a7d1a398260222beb61d5eccc0df80
+oid sha256:c8882b493a4d0b536f2acd4c3773536ec7d328d0c4119c650c8a0ad71faccd17
 size 5048