Training in progress, epoch 1

config.json

@@ -1,74 +1,61 @@
 {
-  "_name_or_path": "facebook/bart-base",
-  "activation_dropout": 0.1,
-  "activation_function": "gelu",
-  "add_bias_logits": false,
-  "add_final_layer_norm": false,
+  "_name_or_path": "t5-base",
   "architectures": [
-    "BartForConditionalGeneration"
+    "T5ForConditionalGeneration"
   ],
-  "attention_dropout": 0.1,
-  "bos_token_id": 0,
-  "classif_dropout": 0.1,
   "classifier_dropout": 0.0,
+  "d_ff": 3072,
+  "d_kv": 64,
   "d_model": 768,
-  "decoder_attention_heads": 12,
-  "decoder_ffn_dim": 3072,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 6,
-  "decoder_start_token_id": 2,
-  "dropout": 0.1,
-  "early_stopping": null,
-  "encoder_attention_heads": 12,
-  "encoder_ffn_dim": 3072,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 6,
-  "eos_token_id": 2,
-  "forced_eos_token_id": 2,
-  "gradient_checkpointing": false,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
-  },
-  "init_std": 0.02,
+  "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,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
-  "max_position_embeddings": 1024,
-  "model_type": "bart",
-  "no_repeat_ngram_size": null,
-  "normalize_before": false,
-  "normalize_embedding": true,
-  "num_beams": null,
-  "num_hidden_layers": 6,
-  "pad_token_id": 1,
-  "scale_embedding": false,
+  "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,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
   "task_specific_params": {
     "summarization": {
-      "length_penalty": 1.0,
-      "max_length": 128,
-      "min_length": 12,
-      "num_beams": 4
-    },
-    "summarization_cnn": {
+      "early_stopping": true,
       "length_penalty": 2.0,
-      "max_length": 142,
-      "min_length": 56,
-      "num_beams": 4
+      "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: "
     },
-    "summarization_xsum": {
-      "length_penalty": 1.0,
-      "max_length": 62,
-      "min_length": 11,
-      "num_beams": 6
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
     }
   },
   "torch_dtype": "float32",
   "transformers_version": "4.46.3",
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 32128
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b2c98d08c8c22010b659f340ddef0ce1abb26a6ae20ed347da885963800f47f
-size 557912620
+oid sha256:60f5c2be547e4e1ecf4b99c6c36994a7e9cb8b50de261bcb17c748897276225e
+size 891644712

runs/Dec07_22-11-11_ws-l4-008/events.out.tfevents.1733595074.ws-l4-008.3926071.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e0736a3e5951a2d65161cdd0011c826eaff5034fef39b4ef8e031e5da691c9f
+size 6200

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7127e444a6ef85d817c654e5a3d4f34c79f862f7e139385b88b188bbcb21060
+oid sha256:4cfd852f405a7746f7a376f2d66f58df804801d71f66f79721e3378cf28c8507
 size 5368