Training in progress, step 500

config.json

@@ -1,40 +1,63 @@
 {
-  "activation_function": "gelu_new",
   "architectures": [
-    "GPT2ForSequenceClassification"
+    "T5ForSequenceClassification"
   ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
-  "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
-  "n_inner": null,
-  "n_layer": 12,
-  "n_positions": 1024,
-  "pad_token_id": 50256,
+  "bos_token_id": 1,
+  "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": 2,
+  "feed_forward_proj": "relu",
+  "gradient_checkpointing": false,
+  "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,
   "problem_type": "single_label_classification",
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
   "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50
+    "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": "4.51.3",
   "use_cache": true,
-  "vocab_size": 50257
+  "vocab_size": 32100
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03d3c4a5c9bf78e2f2cec793081145f33b70510ceb1fc0a81ce30904539d8f08
-size 497780432
+oid sha256:b4a2c592d73a6aa2ebe530db43b69c41db5fc8bf37e3926d2b02d64b2ea909ce
+size 243041240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8142368b9a9d8c4c0f4d0f2af03260bb255e7b623284971711b9f13c52c8a65d
-size 5304
+oid sha256:a94098b415623d7ccb2e79b1f2d25e4a7827b463d63d5f4b24ef2fed9aac5914
+size 5368