Training in progress, epoch 1

.gitattributes

@@ -32,3 +32,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/source.spm filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/target.spm filter=lfs diff=lfs merge=lfs -text
+source.spm filter=lfs diff=lfs merge=lfs -text
+target.spm filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "./models/opus-mt-id-en",
+  "_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": [
+    [
+      54795
+    ]
+  ],
+  "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": 54795,
+  "decoder_vocab_size": 54796,
+  "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,
+  "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": 54795,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 54796
+}

last-checkpoint/config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "./models/opus-mt-id-en",
+  "_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": [
+    [
+      54795
+    ]
+  ],
+  "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": 54795,
+  "decoder_vocab_size": 54796,
+  "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,
+  "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": 54795,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 54796
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_from_model_config": true,
+  "bad_words_ids": [
+    [
+      54795
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 54795,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 6,
+  "pad_token_id": 54795,
+  "transformers_version": "4.26.1"
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4dec0aa40cd861b2c9ad0726d3247d75ed4903b69ff5d63f74db341d2ad0371
+size 577700869

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:476941512fa6d9bf4120703c4b916f3953f36d28ca096772f675e0480ae75f89
+size 289081861

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b17b7c1f5e9b1540ecdd54b5293a612a3c0da8214366d6574f7bd3f50ac48883
+size 14575

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db20625acb7c2081f9bc4169194ebcd4b76101a2460cc48efcde9b3f2e9df3b
+size 627

last-checkpoint/source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a8fefe71c7f26cb0c6aa1b9f0cc0f8d18006b20fe41c547af7f25b9c8333465
+size 800687

last-checkpoint/special_tokens_map.json

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

last-checkpoint/target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e88300911c2c573ec5526777a1e84bae698d20925b82dcef9c7248bb0e537ed0
+size 795925

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "name_or_path": "./models/opus-mt-id-en",
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "id",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "target_lang": "en",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": 1.3274328708648682,
+  "best_model_checkpoint": "models/opus-mt-id-en-open-subtitles/checkpoint-28125",
+  "epoch": 1.0,
+  "global_step": 28125,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.654925800107278e-05,
+      "loss": 1.3533,
+      "step": 28125
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu": 37.6662,
+      "eval_loss": 1.3274328708648682,
+      "eval_runtime": 1861.5149,
+      "eval_samples_per_second": 53.72,
+      "eval_steps_per_second": 1.679,
+      "step": 28125
+    }
+  ],
+  "max_steps": 703125,
+  "num_train_epochs": 25,
+  "total_flos": 5247788925321216.0,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:096873cb715c0742cc88026a10db5fb803013016fd2eb4790edaefea640a8e20
+size 3643

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:476941512fa6d9bf4120703c4b916f3953f36d28ca096772f675e0480ae75f89
+size 289081861

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a8fefe71c7f26cb0c6aa1b9f0cc0f8d18006b20fe41c547af7f25b9c8333465
+size 800687

special_tokens_map.json

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

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e88300911c2c573ec5526777a1e84bae698d20925b82dcef9c7248bb0e537ed0
+size 795925

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "name_or_path": "./models/opus-mt-id-en",
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "id",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "target_lang": "en",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:096873cb715c0742cc88026a10db5fb803013016fd2eb4790edaefea640a8e20
+size 3643