Training in progress, step 1000

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "nsi319/legal-pegasus",
+  "_name_or_path": "google/pegasus-xsum",
   "activation_dropout": 0.1,
   "activation_function": "relu",
   "add_bias_logits": false,
@@ -17,13 +17,15 @@
   "decoder_layerdrop": 0.0,
   "decoder_layers": 16,
   "decoder_start_token_id": 0,
+  "do_blenderbot_90_layernorm": false,
   "dropout": 0.1,
   "encoder_attention_heads": 16,
   "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 16,
   "eos_token_id": 1,
-  "extra_pos_embeddings": 1,
+  "extra_pos_embeddings": 0,
+  "force_bos_token_to_be_generated": false,
   "forced_eos_token_id": 1,
   "gradient_checkpointing": false,
   "id2label": {
@@ -38,14 +40,13 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "length_penalty": 0.8,
+  "length_penalty": 0.6,
   "max_length": 128,
-  "max_position_embeddings": 1024,
-  "min_length": 32,
+  "max_position_embeddings": 512,
   "model_type": "pegasus",
   "normalize_before": true,
   "normalize_embedding": false,
-  "num_beams": 8,
+  "num_beams": 4,
   "num_hidden_layers": 16,
   "pad_token_id": 0,
   "scale_embedding": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f9221002e7b07f701c66ff60296ba51500a0646c2b935dc73251d13759fda9f
-size 2283652852
+oid sha256:2a734ee7325e121c1aacb568aee39d37b8c11fa61bb5e1f2cc8cb84571fcb4ae
+size 2279458540

runs/Apr05_19-42-32_9e6d5516626c/events.out.tfevents.1712346175.9e6d5516626c.440.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6b116cb598053a67746e2ae09e3eb3fbea48f7b708a2b25486b1d86b4e35b99
+size 4184

runs/Apr05_19-45-12_9e6d5516626c/events.out.tfevents.1712346352.9e6d5516626c.3600.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d579c8669fc8e43eefb54bb4025a2beb6508a6cf4deaf2302dde4f06dfad4a8
+size 7014

special_tokens_map.json

@@ -103,8 +103,26 @@
     "<unk_101>",
     "<unk_102>"
   ],
-  "eos_token": "</s>",
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": "<mask_2>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -958,7 +958,7 @@
   "full_tokenizer_file": null,
   "mask_token": "<mask_2>",
   "mask_token_sent": "<mask_1>",
-  "model_max_length": 1024,
+  "model_max_length": 512,
   "offset": 103,
   "pad_token": "<pad>",
   "sp_model_kwargs": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9726e0e27da7b385d2ebc451ea28302f3debe5da9f1e1db012811877ab96274
+oid sha256:943b6226bf1dc2fce9632a2428ae7481bde709ff376897a360adc4a280d61ac7
 size 5112