Training in progress, epoch 1

config.json

@@ -1,44 +1,61 @@
 {
-  "_name_or_path": "Davlan/bert-base-multilingual-cased-finetuned-amharic",
+  "_name_or_path": "google-t5/t5-base",
   "architectures": [
-    "BertForTokenClassification"
+    "T5ForConditionalGeneration"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "directionality": "bidi",
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2",
-    "3": "LABEL_3"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2,
-    "LABEL_3": 3
-  },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "classifier_dropout": 0.0,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "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": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
   "pad_token_id": 0,
-  "pooler_fc_size": 768,
-  "pooler_num_attention_heads": 12,
-  "pooler_num_fc_layers": 3,
-  "pooler_size_per_head": 128,
-  "pooler_type": "first_token_transform",
-  "position_embedding_type": "absolute",
+  "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": "4.45.1",
-  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 119547
+  "vocab_size": 32128
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa14b1f841ba76e853e41334aa09dc5270e1db502efed7b8a670cc50b6bec7f8
-size 709087056
+oid sha256:00deaa080ef9566d03697b0fb430aaf392b094c6724639647c0d1d943725c895
+size 891644712

runs/Nov07_15-43-12_d3102be79e1a/events.out.tfevents.1730994194.d3102be79e1a.30.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d0a82f6e013f40cbbfb1e207b7a064a42afb92a8a7f1a68e19bf37cbc9cb246
+size 6793

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40b3c52fd4d5a7a18517b4d934330762347abed96694f8b759320e82ef8250fd
+oid sha256:ce02d7ef87d20f4be47ea53c8e22bba7bb1e3b67ca4222581b2af5c5e1287f34
 size 5304