Training in progress, step 45

config.json

@@ -1,24 +1,62 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "research-backup/t5-small-tweetqa-qag-np",
+  "add_prefix": false,
   "architectures": [
-    "DistilBertForQuestionAnswering"
+    "T5ForConditionalGeneration"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
-  "initializer_range": 0.02,
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "output_past": true,
   "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
   "torch_dtype": "float32",
   "transformers_version": "4.44.0.dev0",
-  "vocab_size": 30522
+  "use_cache": true,
+  "vocab_size": 32101
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:940876f211e1aa7225f65edc91d0d4c47525518b47f8ab72b33a0570c00cc17f
-size 265470032
+oid sha256:4be3dde061179dd663cd7b58f51a9934a3e2c344b065402b43c3bf2d1809a45f
+size 241986600

runs/Jul25_15-49-00_5ce261332ea8/events.out.tfevents.1721922543.5ce261332ea8.1254.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f25c4aadd6caf6848599ee6b67d382cecfe087d4305fc83d43ec84793aec509a
+size 6973

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc197820c86b244c14b1072e9c168c9bd0ea4184a1f18c20423128903292c5c2
-size 5112
+oid sha256:b8b9c7a34efad9655456f16c348eeb00b98d08c54f366d2e863673c6f09e498d
+size 5240