Training in progress, step 10

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/bart-base",
+  "_name_or_path": "benjamintli/bart-midi",
   "activation_dropout": 0.1,
   "activation_function": "gelu",
   "add_bias_logits": false,
@@ -18,13 +18,12 @@
   "decoder_layers": 6,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
-  "early_stopping": true,
+  "early_stopping": null,
   "encoder_attention_heads": 12,
   "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 6,
   "eos_token_id": 2,
-  "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
   "id2label": {
@@ -41,10 +40,10 @@
   },
   "max_position_embeddings": 1024,
   "model_type": "bart",
-  "no_repeat_ngram_size": 3,
+  "no_repeat_ngram_size": null,
   "normalize_before": false,
   "normalize_embedding": true,
-  "num_beams": 4,
+  "num_beams": null,
   "num_hidden_layers": 6,
   "pad_token_id": 1,
   "scale_embedding": false,
@@ -69,7 +68,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.47.1",
   "use_cache": true,
   "vocab_size": 80265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bdd0cf6d9a2e977046351f4f820b386f54ef174ff22e3122c43496e1489539c
+oid sha256:c37ad237a83799b573173a3efb17008c04675a08564511618b981025ec528f0b
 size 650192620

tokenizer_config.json

@@ -47,6 +47,7 @@
   "cls_token": "<s>",
   "eos_token": "</s>",
   "errors": "replace",
+  "extra_special_tokens": {},
   "mask_token": "<mask>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5481fc6bade3f8f522b15280db35bfccc1a177152779f0d0a9b7802eca076bc9
-size 5176
+oid sha256:2006fd6c3a9e1f4517d3e06196a3c3d80dc1f27d3f243abdf8bde2f3d2bd3675
+size 5304