Training in progress, step 500

config.json

@@ -1,58 +1,61 @@
 {
-  "_name_or_path": "facebook/mbart-large-50",
-  "_num_labels": 3,
-  "activation_dropout": 0.0,
-  "activation_function": "gelu",
-  "add_bias_logits": false,
-  "add_final_layer_norm": true,
+  "_name_or_path": "google-t5/t5-small",
   "architectures": [
-    "MBartForConditionalGeneration"
+    "T5ForConditionalGeneration"
   ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "classif_dropout": 0.0,
   "classifier_dropout": 0.0,
-  "d_model": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 12,
-  "decoder_start_token_id": 2,
-  "dropout": 0.1,
-  "early_stopping": true,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 12,
-  "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,
+  "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,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
-  "max_length": 200,
-  "max_position_embeddings": 1024,
-  "model_type": "mbart",
-  "normalize_before": true,
-  "normalize_embedding": true,
-  "num_beams": 5,
-  "num_hidden_layers": 12,
+  "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": 1,
-  "scale_embedding": true,
-  "static_position_embeddings": false,
-  "tokenizer_class": "MBart50Tokenizer",
+  "pad_token_id": 0,
+  "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": "4.40.2",
   "use_cache": true,
-  "vocab_size": 250054
+  "vocab_size": 32128
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fcf37a910b0311b01f94b85ab2cb38ee289434f30d446d17932891b26406438
-size 2444578688
+oid sha256:ed4da9609b4926101835e04b0ac50b77dae562b5da4bd043074cf32400d7d176
+size 242041896

runs/May16_16-01-19_9793e7c94c5c/events.out.tfevents.1715875311.9793e7c94c5c.260.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87d3975c96cb8ba7363d1680eebfe18bef823fa3fefb3d4158d23069f92d370e
+size 5678

runs/May16_16-12-17_9793e7c94c5c/events.out.tfevents.1715875953.9793e7c94c5c.260.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d330f4a84d98faf449b1c88a9e0df277c41ef77fdfa23c0565271ae6e90b1637
+size 5917

special_tokens_map.json

@@ -53,9 +53,27 @@
     "gl_ES",
     "sl_SI"
   ],
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -63,7 +81,25 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef126060ddcab67250020d3e4fff2150e3946ba9e7cea24b2a18dd969e0469da
-size 17110019
+oid sha256:2e05149e476a633a1848f49e8aab40803980b7a22e1a0829229378759c819049
+size 17094668

tokenizer_config.json

@@ -516,12 +516,16 @@
   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": "<mask>",
+  "max_length": 128,
   "model_max_length": 1024,
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "sp_model_kwargs": {},
   "src_lang": "en_XX",
+  "stride": 0,
   "tgt_lang": null,
   "tokenizer_class": "MBart50Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:644d8c1b25bfb71f2598b5777a5d7dbbfdb15371650e3ebac5213d53ecbdfcfa
+oid sha256:3fdf72f1d7ffacb8feaa63a0ab7593871ba4fb00df201fc60381d909e1d9b137
 size 5112