Update from

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-de",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      58100
+    ]
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 58100,
+  "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,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 58100,
+  "scale_embedding": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.2",
+  "use_cache": true,
+  "vocab_size": 58101
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede6643607c72cfe883ca1cfdea31d6a7b9210b637e78113ccb5c1894f818f4b
+size 591236557

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acd50b2fa2189f4b018a0a0226ef02a8661e3566dd9f2bcf18a981c902b1659f
+size 295861701

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6c7d65e92a20df762b2ecaa8afbf893d9d59545e50c8d18c24085a9d2f4cd21
+size 15523

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:405091d29df97a8772f322737eb40c2cd7c84c343630b70fa67dcfd831a1eb08
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d6b383713ee2934a188eb99d782d85ed13340875769036e5d1ad11efbeeb0ae
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"source_lang": "en", "target_lang": "de", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "Helsinki-NLP/opus-mt-en-de", "tokenizer_class": "MarianTokenizer"}

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.03517336953845505,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.9929653260923093e-05,
+      "loss": 2.0913,
+      "step": 500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.985930652184618e-05,
+      "loss": 2.0515,
+      "step": 1000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.978895978276927e-05,
+      "loss": 2.0554,
+      "step": 1500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9718613043692362e-05,
+      "loss": 2.0336,
+      "step": 2000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.964826630461545e-05,
+      "loss": 2.0487,
+      "step": 2500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9577919565538542e-05,
+      "loss": 2.0338,
+      "step": 3000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.950757282646163e-05,
+      "loss": 2.0361,
+      "step": 3500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9437226087384722e-05,
+      "loss": 2.0281,
+      "step": 4000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9367020041785966e-05,
+      "loss": 2.0136,
+      "step": 4500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9296673302709054e-05,
+      "loss": 2.0301,
+      "step": 5000
+    }
+  ],
+  "max_steps": 142153,
+  "num_train_epochs": 1,
+  "total_flos": 6948342774890496.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aa5d901a2753ad635f8f0561777927558e8c4f01fb37bb25c7dd9902d6df112
+size 2735