Training in progress, step 200

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "facebook/mbart-large-cc25",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "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,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": 1024,
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "normalize_before": true,
+  "normalize_embedding": true,
+  "num_beams": 5,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "task_specific_params": {
+    "translation_en_to_ro": {
+      "decoder_start_token_id": 250020
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "use_cache": true,
+  "vocab_size": 250027
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3fbc0021ef1ecf9015f76a175975619f8a844f3a556bc22bb5103f81a9c0de5
+size 2444467988

runs/Feb01_09-43-15_7651e58a36e1/events.out.tfevents.1706780598.7651e58a36e1.115.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0791e523d6dcbf91c3dc47b0295aa3e3de55661177d166c407cc31ad13c9ac55
+size 5210

runs/Feb01_09-43-32_7651e58a36e1/events.out.tfevents.1706780615.7651e58a36e1.115.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:529ce6874e0f23fc02228e55ab52a3fb8534be42dc652af15207287386237270
+size 10332

runs/Feb01_09-45-36_7651e58a36e1/events.out.tfevents.1706780741.7651e58a36e1.115.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:389e20272bcc9c0810ec5496c20f9f42ecd4e8d850526abc110067dc7e0ca787
+size 10760

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abcb5f79e16bf251fadb8c6b0de5051d61372e7462afa3fd6c92d2cc647809e8
+size 4856