Training in progress, step 500

config.json

@@ -1,59 +1,46 @@
 {
-  "_name_or_path": "facebook/mbart-large-50",
-  "_num_labels": 3,
-  "activation_dropout": 0.0,
-  "activation_function": "gelu",
-  "add_bias_logits": false,
-  "add_final_layer_norm": true,
+  "_name_or_path": "distilgpt2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
   "architectures": [
-    "MBartForCausalLM"
+    "GPT2LMHeadModel"
   ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "classif_dropout": 0.0,
-  "classifier_dropout": 0.0,
-  "d_model": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 12,
-  "decoder_start_token_id": 2,
-  "dropout": 0.1,
-  "early_stopping": true,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 12,
-  "eos_token_id": 2,
-  "forced_eos_token_id": 2,
-  "gradient_checkpointing": false,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
   "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
+    "0": "LABEL_0"
   },
-  "init_std": 0.02,
-  "is_decoder": true,
-  "is_encoder_decoder": false,
+  "initializer_range": 0.02,
   "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
+    "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
+    }
   },
-  "max_length": 200,
-  "max_position_embeddings": 1024,
-  "model_type": "mbart",
-  "normalize_before": true,
-  "normalize_embedding": true,
-  "num_beams": 5,
-  "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
-  "scale_embedding": true,
-  "static_position_embeddings": false,
-  "tokenizer_class": "MBart50Tokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
   "use_cache": true,
-  "vocab_size": 250054
+  "vocab_size": 50257
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09c11930a281b98439733c553e6f482636e0bd0f6f7286612a36618f082c27fb
-size 1834718496
+oid sha256:047320cc62f2a1d13e0bc5d267e8cacba2dc4d3d900742baa806adac7b7c11d4
+size 327657928

runs/Dec21_09-45-07_c9a43a2dc54c/events.out.tfevents.1703151908.c9a43a2dc54c.2930.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:225e8bb31d30066c15761ca07e0c0492c4ee5931f55c0c08860c539861541620
+size 4733

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec444722bef4263f04d71bb6717e791f7af90334179008a6f4b1066ff73c394
+oid sha256:b4869012ebe7b521d7de93948f5554b637538b9323ffd8f9c6d3ae3fbc00798a
 size 4600