en-de model

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 12.0,
+    "eval_bleu": 16.0242,
+    "eval_gen_len": 259.6051,
+    "eval_loss": 2.603928565979004,
+    "eval_runtime": 980.879,
+    "eval_samples": 1674,
+    "eval_samples_per_second": 1.707,
+    "eval_steps_per_second": 0.214,
+    "train_loss": 0.873852771146011,
+    "train_runtime": 13341.3267,
+    "train_samples": 3349,
+    "train_samples_per_second": 3.012,
+    "train_steps_per_second": 0.377
+}

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "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": "4.13.0.dev0",
+  "use_cache": true,
+  "vocab_size": 58101
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 12.0,
+    "eval_bleu": 16.0242,
+    "eval_gen_len": 259.6051,
+    "eval_loss": 2.603928565979004,
+    "eval_runtime": 980.879,
+    "eval_samples": 1674,
+    "eval_samples_per_second": 1.707,
+    "eval_steps_per_second": 0.214
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8845225403eee2bb0c44ca977a615410ce5fbf6a6adb74dba93a0c83f0cab4d6
+size 295861701

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": "opus-mt-en-de", "tokenizer_class": "MarianTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 12.0,
+    "train_loss": 0.873852771146011,
+    "train_runtime": 13341.3267,
+    "train_samples": 3349,
+    "train_samples_per_second": 3.012,
+    "train_steps_per_second": 0.377
+}

trainer_state.json

@@ -0,0 +1,151 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 12.0,
+  "global_step": 5028,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_bleu": 15.5532,
+      "eval_gen_len": 262.7814,
+      "eval_loss": 2.603503942489624,
+      "eval_runtime": 1071.2105,
+      "eval_samples_per_second": 1.563,
+      "eval_steps_per_second": 0.196,
+      "step": 419
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 15.8442,
+      "eval_gen_len": 249.9671,
+      "eval_loss": 2.534031629562378,
+      "eval_runtime": 974.071,
+      "eval_samples_per_second": 1.719,
+      "eval_steps_per_second": 0.216,
+      "step": 838
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 15.4747,
+      "eval_gen_len": 274.1971,
+      "eval_loss": 2.492140293121338,
+      "eval_runtime": 1054.8804,
+      "eval_samples_per_second": 1.587,
+      "eval_steps_per_second": 0.199,
+      "step": 1257
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 16.1199,
+      "eval_gen_len": 258.5263,
+      "eval_loss": 2.5081911087036133,
+      "eval_runtime": 967.203,
+      "eval_samples_per_second": 1.731,
+      "eval_steps_per_second": 0.217,
+      "step": 1676
+    },
+    {
+      "epoch": 5.0,
+      "eval_bleu": 16.2089,
+      "eval_gen_len": 260.6117,
+      "eval_loss": 2.512809991836548,
+      "eval_runtime": 986.3606,
+      "eval_samples_per_second": 1.697,
+      "eval_steps_per_second": 0.213,
+      "step": 2095
+    },
+    {
+      "epoch": 6.0,
+      "eval_bleu": 16.0677,
+      "eval_gen_len": 256.6434,
+      "eval_loss": 2.532682180404663,
+      "eval_runtime": 972.4474,
+      "eval_samples_per_second": 1.721,
+      "eval_steps_per_second": 0.216,
+      "step": 2514
+    },
+    {
+      "epoch": 7.0,
+      "eval_bleu": 15.9211,
+      "eval_gen_len": 254.4606,
+      "eval_loss": 2.5517630577087402,
+      "eval_runtime": 947.2841,
+      "eval_samples_per_second": 1.767,
+      "eval_steps_per_second": 0.222,
+      "step": 2933
+    },
+    {
+      "epoch": 8.0,
+      "eval_bleu": 16.022,
+      "eval_gen_len": 257.5149,
+      "eval_loss": 2.563725709915161,
+      "eval_runtime": 962.17,
+      "eval_samples_per_second": 1.74,
+      "eval_steps_per_second": 0.218,
+      "step": 3352
+    },
+    {
+      "epoch": 9.0,
+      "eval_bleu": 16.0511,
+      "eval_gen_len": 258.0084,
+      "eval_loss": 2.5875699520111084,
+      "eval_runtime": 962.6535,
+      "eval_samples_per_second": 1.739,
+      "eval_steps_per_second": 0.218,
+      "step": 3771
+    },
+    {
+      "epoch": 10.0,
+      "eval_bleu": 16.0276,
+      "eval_gen_len": 257.9409,
+      "eval_loss": 2.589696168899536,
+      "eval_runtime": 968.2157,
+      "eval_samples_per_second": 1.729,
+      "eval_steps_per_second": 0.217,
+      "step": 4190
+    },
+    {
+      "epoch": 11.0,
+      "eval_bleu": 15.9876,
+      "eval_gen_len": 258.5191,
+      "eval_loss": 2.600374221801758,
+      "eval_runtime": 972.9329,
+      "eval_samples_per_second": 1.721,
+      "eval_steps_per_second": 0.216,
+      "step": 4609
+    },
+    {
+      "epoch": 11.93,
+      "learning_rate": 2.7844073190135243e-07,
+      "loss": 0.8761,
+      "step": 5000
+    },
+    {
+      "epoch": 12.0,
+      "eval_bleu": 16.0242,
+      "eval_gen_len": 259.6051,
+      "eval_loss": 2.603928565979004,
+      "eval_runtime": 980.0259,
+      "eval_samples_per_second": 1.708,
+      "eval_steps_per_second": 0.214,
+      "step": 5028
+    },
+    {
+      "epoch": 12.0,
+      "step": 5028,
+      "total_flos": 5449229958905856.0,
+      "train_loss": 0.873852771146011,
+      "train_runtime": 13341.3267,
+      "train_samples_per_second": 3.012,
+      "train_steps_per_second": 0.377
+    }
+  ],
+  "max_steps": 5028,
+  "num_train_epochs": 12,
+  "total_flos": 5449229958905856.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85a7ee2afe7d665344e6c12cd6137c16b4df007f58f1b9aefb39e1ff034a7b67
+size 2991