Training in progress, step 500

config.json

@@ -1,28 +1,63 @@
 {
-  "_name_or_path": "roberta-base",
+  "_name_or_path": "facebook/blenderbot_small-90M",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
   "architectures": [
-    "RobertaForCausalLM"
+    "BlenderbotSmallForCausalLM"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 512,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 8,
+  "decoder_start_token_id": 1,
+  "do_blenderbot_90_layernorm": true,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 8,
   "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "extra_pos_embeddings": 0,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
   "is_decoder": true,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "is_encoder_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layernorm_variant": "xlm",
+  "length_penalty": 0.65,
+  "max_length": 128,
+  "max_position_embeddings": 512,
+  "min_length": 20,
+  "model_type": "blenderbot-small",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 10,
+  "num_hidden_layers": 8,
+  "pad_token_id": 0,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.40.0",
-  "type_vocab_size": 1,
+  "unk_token_id": 3,
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 54944
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:710aad63a9a9277a23e195bd97866122adbc7fa9c5be99160c7b60aac4bc64ec
-size 498813948
+oid sha256:f07144c76f01ec0fb47e5b6891d48605124fcce5277c9ccbac7c838ad986de55
+size 248131760

runs/Apr25_09-03-49_818c51180a1a/events.out.tfevents.1714035830.818c51180a1a.212.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:164247c65b69283f7c494d52ee7b4ea4a02a2a398005785fb2237b40a485da6f
+size 5819

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac3d69a2e3b591534364a4c835986a52d54d8be9bf995c7d39b707d727168dc6
+oid sha256:9926be09720d4adbe07d947f3d15a639fcb661698b2586e847fce5bd0164e88a
 size 4984