Added all files from model checkpoint-62500 for vocab_size 20000, 10 epochs

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "/tmp/Helsinki-NLP/opus-mt-en-ro",
+  "_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": [
+    [
+      0
+    ]
+  ],
+  "bos_token_id": 1,
+  "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": 3,
+  "decoder_vocab_size": 20001,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 0,
+  "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": 3,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 20001
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_from_model_config": true,
+  "bad_words_ids": [
+    [
+      0
+    ]
+  ],
+  "bos_token_id": 1,
+  "decoder_start_token_id": 3,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 3,
+  "transformers_version": "4.26.0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b09aaaeb48e0f8474aaeb8b472917c005ead044310bae8fd1b145b0a17d6b2f1
+size 435180549

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c47868b626fe48cbaca8248d55c79010e5d8de5788b92e7dc89e4d9f2b5b8a7
+size 217682565

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1321806b2dca78c343dd16f11f0f25263239484764ca32b5c309b4388a31dd0b
+size 14575

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e68668651c60748eaaec882baa4b1f243e000fb9a37a9c5f0fa89d100fa1a1df
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:571cbe705e7b8a55ee94dc123b0b79849bcbb95e812f8eba2ef4b4bd7b88dc2f
+size 627

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "name_or_path": "marian-mt-hu-ro-20000",
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": null,
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "target_lang": null,
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 62500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.9333333333333333e-05,
+      "loss": 5.4183,
+      "step": 6250
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.866688e-05,
+      "loss": 4.1174,
+      "step": 12500
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.8000533333333335e-05,
+      "loss": 3.5049,
+      "step": 18750
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.7334080000000003e-05,
+      "loss": 3.0671,
+      "step": 25000
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.6667626666666667e-05,
+      "loss": 2.7197,
+      "step": 31250
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 1.600128e-05,
+      "loss": 2.4474,
+      "step": 37500
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 1.533482666666667e-05,
+      "loss": 2.2439,
+      "step": 43750
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 1.4668373333333334e-05,
+      "loss": 2.091,
+      "step": 50000
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 1.4001920000000002e-05,
+      "loss": 1.9731,
+      "step": 56250
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 1.3335360000000002e-05,
+      "loss": 1.8787,
+      "step": 62500
+    }
+  ],
+  "max_steps": 187500,
+  "num_train_epochs": 30,
+  "total_flos": 1.1680685027544269e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:664e6fb97ea1712a9e07495fe2f23263e6753d0f1182959510e60619ab45de44
+size 3643