Initial model commit

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "best_ckpt_igbo_en/best_ckpt13point73",
+  "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": [
+    [
+      64171
+    ]
+  ],
+  "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": 64171,
+  "decoder_vocab_size": 64172,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "extra_pos_embeddings": 64172,
+  "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": 6,
+  "num_hidden_layers": 6,
+  "pad_token_id": 64171,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "use_cache": true,
+  "vocab_size": 64172
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "bad_words_ids": [
+    [
+      64171
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 64171,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 6,
+  "pad_token_id": 64171,
+  "transformers_version": "4.28.0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89fb9206e166fc785adbdc7d499bfc34a6e9f45f8332c907d9bbb0f1225084e0
+size 616104709

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a895d39b9b885cf5ce65748d87367041368add7b1b7851617043aa8a3079bfe
+size 308321413

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:235c3be90cf2af063f1e052db0d724f2b37bdfadb6927b4165c99312a996a6fd
+size 14575

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfa3bcfad6548e955614aa66924075e0bfa36d4a9baf6cf6190c3fd577b6da91
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5014f29fb8708ceda693769399163512ddef57fbe018df5e707ea8bafb71540f
+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 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "mul",
+  "sp_model_kwargs": {},
+  "target_lang": "eng",
+  "tokenizer_class": "MarianTokenizer",
+  "tokenizer_file": null,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,26 @@
+{
+  "best_metric": 3.0208277702331543,
+  "best_model_checkpoint": "./marianMT_experiment/NEW/./checkpoint-50",
+  "epoch": 5.813953488372093,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.81,
+      "eval_BLEU_ibo": 18.1404,
+      "eval_BLEU_mean": 18.1404,
+      "eval_loss": 3.0208277702331543,
+      "eval_runtime": 39.0165,
+      "eval_samples_per_second": 12.815,
+      "eval_steps_per_second": 3.204,
+      "step": 50
+    }
+  ],
+  "max_steps": 120,
+  "num_train_epochs": 15,
+  "total_flos": 4881252790960128.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a923134b19ece4bfe3fca807016e8b50ece57c03b7524160e03b9fc417224a74
+size 3707