Training in progress, epoch 1

config.json

@@ -0,0 +1,71 @@
+{
+  "_name_or_path": "google/flan-t5-xl",
+  "architectures": [
+    "T5ForSequenceClassification"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 5120,
+  "d_kv": 64,
+  "d_model": 2048,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "id2label": {
+    "0": "P",
+    "1": "S"
+  },
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "label2id": {
+    "P": 0,
+    "S": 1
+  },
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 24,
+  "num_heads": 32,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "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: "
+    }
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

runs/Mar18_17-33-09_thor/events.out.tfevents.1710779592.thor.259521.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31d731fd0ff3aa44fcd398c7171f5733e65b5899faf2d4b7cde8c00c2c076fe9
+size 5427

runs/Mar18_17-34-09_thor/events.out.tfevents.1710779652.thor.259974.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10d57179a1b8a42ece39c7c238da852552b1b6592b35dbf7de7650a1c356ff3c
+size 4184

runs/Mar18_17-34-53_thor/events.out.tfevents.1710779696.thor.260447.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaf5521e0de6c145c842558b56e2744040f79647dfd90321c1e7c3e2b039529d
+size 5427

runs/Mar18_17-36-20_thor/events.out.tfevents.1710779782.thor.260979.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dffa59bafe6ffc757cc5a3ee6c51324a2c66c3e133963c6a5ea6ae229861eac5
+size 6406

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d8c34f70fbcb027419c51bd399a6930dc0a6eb61fa75aa30d5b18dda0da64c5
+size 4792