Training in progress, step 500

config.json

@@ -18,7 +18,6 @@
   "decoder_layers": 6,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
-  "early_stopping": true,
   "encoder_attention_heads": 12,
   "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
@@ -39,7 +38,10 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
+  "length_penalty": 1.2,
+  "max_length": 256,
   "max_position_embeddings": 1024,
+  "min_length": 50,
   "model_type": "bart",
   "no_repeat_ngram_size": 3,
   "normalize_before": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efb2719d0b0f4fc2e2025f277b53de854375b8576edd4158b80ea938c83964e9
+oid sha256:56938d75cbab457875dd9ce9296f54ddf52e4edbf4aeb5af423e3b2b3d351e4f
 size 557912620

runs/Feb08_17-39-21_4b007708813c/events.out.tfevents.1707414174.4b007708813c.408.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbc3711dc2eca2946947a4aa6918de23346afe832260f5ed1bfc5fff55fd123b
+size 5684

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 128,
+    "max_length": 256,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dc1b0a6f82b9cd92e36b9d17cd37cb679e67a9ff7090aa2000954231e5354dc
+oid sha256:b0ce2e762da71668d7ef15e1aff9dd0a486902fe60fc973ed2634658fadb6bcb
 size 4728