Training complete

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: google/mt5-small
+base_model: Helsinki-NLP/opus-mt-en-fr
 tags:
 - summarization
 - generated_from_trainer
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mt5-small-finetuned-amazon-en-es
 
-This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-fr](https://huggingface.co/Helsinki-NLP/opus-mt-en-fr) on an unknown dataset.
 
 ## Model description
 
@@ -38,13 +38,12 @@ The following hyperparameters were used during training:
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - num_epochs: 8
 
 ### Framework versions
 
-- Transformers 4.45.2
+- Transformers 4.46.2
 - Pytorch 2.5.1+cu121
-- Datasets 3.1.0
 - Tokenizers 0.20.3

config.json

@@ -1,32 +1,57 @@
 {
-  "_name_or_path": "google/mt5-small",
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-fr",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
   "architectures": [
-    "MT5ForConditionalGeneration"
+    "MarianMTModel"
   ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
   "classifier_dropout": 0.0,
-  "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,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 59513,
+  "decoder_vocab_size": 59514,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
   "is_encoder_decoder": true,
-  "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",
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 59513,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.45.2",
+  "transformers_version": "4.46.2",
   "use_cache": true,
-  "vocab_size": 250112
+  "vocab_size": 59514
 }

generation_config.json

@@ -1,7 +1,16 @@
 {
-  "_from_model_config": true,
-  "decoder_start_token_id": 0,
-  "eos_token_id": 1,
-  "pad_token_id": 0,
-  "transformers_version": "4.45.2"
+  "bad_words_ids": [
+    [
+      59513
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 59513,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 59513,
+  "renormalize_logits": true,
+  "transformers_version": "4.46.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3000aee8d618670e7095d6ad5d223437cb645b0bd2c1fe8eb49f25d127608bc
-size 1200729512
+oid sha256:ede839818461da667bc69127cc14b16be6af7785fa967a3de8c487d5a7b346c7
+size 298705768

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29d8e418039a408da274b334130e7132bb7505ec065cc9bb4bc0f880d2b542a6
-size 5368
+oid sha256:8f716a7174863007fe08b25a46fa51e7fe30d0e4449e7fd6b826c1838ed44639
+size 5496