Model save

README.md

@@ -1,6 +1,6 @@
 ---
-license: mit
-base_model: facebook/bart-large-cnn
+license: apache-2.0
+base_model: huggingface-course/mt5-finetuned-amazon-en-es
 tags:
 - generated_from_trainer
 model-index:
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # my_fine_tuned_t5_small_model
 
-This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the None dataset.
+This model is a fine-tuned version of [huggingface-course/mt5-finetuned-amazon-en-es](https://huggingface.co/huggingface-course/mt5-finetuned-amazon-en-es) on the None dataset.
 
 ## Model description
 

config.json

@@ -1,70 +1,32 @@
 {
-  "_name_or_path": "facebook/bart-large-cnn",
-  "_num_labels": 3,
-  "activation_dropout": 0.0,
-  "activation_function": "gelu",
-  "add_final_layer_norm": false,
+  "_name_or_path": "huggingface-course/mt5-finetuned-amazon-en-es",
   "architectures": [
-    "BartForConditionalGeneration"
+    "MT5ForConditionalGeneration"
   ],
-  "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,
-  "force_bos_token_to_be_generated": true,
-  "forced_bos_token_id": 0,
-  "forced_eos_token_id": 2,
-  "gradient_checkpointing": false,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
-  },
-  "init_std": 0.02,
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
   "is_encoder_decoder": true,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
-  "length_penalty": 2.0,
-  "max_length": 142,
-  "max_position_embeddings": 1024,
-  "min_length": 56,
-  "model_type": "bart",
-  "no_repeat_ngram_size": 3,
-  "normalize_before": false,
-  "num_beams": 4,
-  "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": 1,
-  "prefix": " ",
-  "scale_embedding": false,
-  "task_specific_params": {
-    "summarization": {
-      "early_stopping": true,
-      "length_penalty": 2.0,
-      "max_length": 142,
-      "min_length": 56,
-      "no_repeat_ngram_size": 3,
-      "num_beams": 4
-    }
-  },
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "mt5",
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
   "use_cache": true,
-  "vocab_size": 50264
+  "vocab_size": 250112
 }

generation_config.json

@@ -1,16 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 0,
-  "decoder_start_token_id": 2,
-  "early_stopping": true,
-  "eos_token_id": 2,
-  "forced_bos_token_id": 0,
-  "forced_eos_token_id": 2,
-  "length_penalty": 2.0,
-  "max_length": 142,
-  "min_length": 56,
-  "no_repeat_ngram_size": 3,
-  "num_beams": 4,
-  "pad_token_id": 1,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
   "transformers_version": "4.41.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22f4585decfbc15373fc9ed5f5aecfb3748a3f63cbd2116854564e26a60dc5bb
-size 1625422896
+oid sha256:bbda38569c7a4ad70a93f9381de845b45326d5d63a27a817ffad980d3fb6ff2e
+size 1200729512

runs/Jun09_11-00-37_DESKTOP-H2CRQMR/events.out.tfevents.1717905639.DESKTOP-H2CRQMR.573843.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ccec20c7c1283d67293210305b97e4c2e7f8599243879ea9081efd98c329f5a
+size 4184

runs/Jun09_11-02-05_DESKTOP-H2CRQMR/events.out.tfevents.1717905727.DESKTOP-H2CRQMR.574289.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b2c851ac76020ecb5c54b517c9dbd655e585e9dfc8e8151dbf3dc8bf7c2de90
+size 5532

special_tokens_map.json

@@ -1,15 +1,23 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
     "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
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

spiece.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
-size 791656
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76875c73585f5ec48386c5b75680bfc0ccf3c93c2939d4a25b7018d57c7f5881
-size 2108642
+oid sha256:4ee660ae764cd56ecac9dbe82d766502034efac119fc579414afcd68d4f6b922
+size 16315191

tokenizer_config.json

@@ -1,57 +1,41 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
       "content": "<pad>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
+    "1": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
+    "2": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "50264": {
-      "content": "<mask>",
-      "lstrip": true,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
+  "additional_special_tokens": [],
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
   "eos_token": "</s>",
-  "errors": "replace",
-  "mask_token": "<mask>",
+  "extra_ids": 0,
+  "max_length": 30,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "BartTokenizer",
-  "trim_offsets": true,
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "T5Tokenizer",
+  "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 sha256:3b91e26723f42ede66c6bc1f60c4ea02a4cb333030ec602b2e3ca718d27b3a61
+oid sha256:057ba6b3e378917b7b26a05a3ad39c15647e3562224cd7526fab41de30725ad8
 size 5304