Training in progress, step 1000

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/pegasus-xsum",
+  "_name_or_path": "nsi319/legal-pegasus",
   "activation_dropout": 0.1,
   "activation_function": "relu",
   "add_bias_logits": false,
@@ -17,15 +17,13 @@
   "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": 0,
-  "force_bos_token_to_be_generated": false,
+  "extra_pos_embeddings": 1,
   "forced_eos_token_id": 1,
   "gradient_checkpointing": false,
   "id2label": {
@@ -40,9 +38,10 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "length_penalty": 0.6,
-  "max_length": 64,
-  "max_position_embeddings": 512,
+  "length_penalty": 0.8,
+  "max_length": 128,
+  "max_position_embeddings": 1024,
+  "min_length": 32,
   "model_type": "pegasus",
   "normalize_before": true,
   "normalize_embedding": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ce84b22a6ddd8d255b60fee4af399c8a9942be6a755e0c447d82dea52c8cd79
-size 2279458540
+oid sha256:04d1aaefe1155b3fc6a5cc4d972b82b4529e6676d55c8d685cc5c60719056b34
+size 2283652852

runs/Apr05_11-38-26_96cc1a9ffaae/events.out.tfevents.1712317110.96cc1a9ffaae.208.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44cc848883b66a1e95dac1a51a0411180236f42f51536d5a0d3f2e1e3cb4b7e6
+size 5447

runs/Apr05_11-44-18_96cc1a9ffaae/events.out.tfevents.1712317460.96cc1a9ffaae.4071.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed1bc70c5ccd6575496d4ef24a58374fd4e68cd7264264c53e9bf96764b0e92
+size 6953

special_tokens_map.json

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

tokenizer_config.json

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71af382a9d48accd0cf61043ae64898d33cb92fd3e2c6b0a5c48263e35cecab1
+oid sha256:f9726e0e27da7b385d2ebc451ea28302f3debe5da9f1e1db012811877ab96274
 size 5112