Training in progress, step 500

config.json

@@ -29,7 +29,7 @@
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.37.2",
   "use_cache": true,
   "vocab_size": 32128
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a48aa0e51ce59ad533ba6ecc440912b21eb78dc9fe3c992c45ee02bd3aea9846
-size 1187780840
+oid sha256:ee5595a3fc31465d327306ba5fea63893ab1997910a911b9f5ad94ca6f2ef2b4
+size 990386200

runs/Oct18_14-22-24_user/events.out.tfevents.1729241545.user.881855.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e66bcd2fabfb53d1427df21d22d107f75456dd28cc1805c31b5f82b01ff4a84d
-size 4913
+oid sha256:d099a53c633a965c53e2ac90d9481bcdbcfa50ea8c3921c9bcf4ded9021c05b9
+size 5070

runs/Oct18_14-29-37_user/events.out.tfevents.1729241978.user.897992.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34cc229fa86a60567ce95f75db5b83ba0de6386c586517fc56d7f4aae7c92a57
+size 4756

runs/Oct18_14-32-11_user/events.out.tfevents.1729242132.user.903616.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:003fccbc6e771c82c450b5842501e0e1dc2b31ad46d24567de1e10e6bb646209
+size 4912

tmp-checkpoint-1000/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "google/long-t5-tglobal-base",
+  "architectures": [
+    "LongT5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "encoder_attention_type": "transient-global",
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "global_block_size": 16,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "local_radius": 127,
+  "model_type": "longt5",
+  "n_positions": 4096,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

tmp-checkpoint-1000/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "max_length": 100,
+  "pad_token_id": 0,
+  "transformers_version": "4.37.2"
+}

tokenizer.json

@@ -944,8 +944,8 @@
       {
         "type": "Metaspace",
         "replacement": "▁",
-        "prepend_scheme": "always",
-        "split": true
+        "add_prefix_space": true,
+        "prepend_scheme": "always"
       }
     ]
   },
@@ -1006,8 +1006,8 @@
   "decoder": {
     "type": "Metaspace",
     "replacement": "▁",
-    "prepend_scheme": "always",
-    "split": true
+    "add_prefix_space": true,
+    "prepend_scheme": "always"
   },
   "model": {
     "type": "Unigram",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8805c651b82276f5cf6a5a2a6843438815d5d22ad05c022db4c2447902ae2ea5
-size 5304
+oid sha256:12baebc311057f540511447a75d2b6748971ea944b525d1a05b0a6585b60060e
+size 4856