Training in progress epoch 0

.gitattributes

@@ -32,3 +32,5 @@ 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
+source.spm filter=lfs diff=lfs merge=lfs -text
+target.spm filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,2 @@
+step_*
+epoch_*

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<brk>": 59514
+}

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "context-mt/iwslt17-marian-small-ctx4-cwd1-en-fr",
+  "_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": [
+    [
+      59513
+    ]
+  ],
+  "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": 59513,
+  "decoder_vocab_size": 59515,
+  "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": 59513,
+  "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": 59515
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_from_model_config": true,
+  "bad_words_ids": [
+    [
+      59513
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 59513,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 59513,
+  "transformers_version": "4.28.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bdbf96e15fc59f43c2f39d5d3e9800384f57ab42761c54f9ccc9bb995698a28
+size 298765253

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:173e9f493a668fe396d599e28d414a201193094e6ffd7a4678e5aab0f6d3d838
+size 778395

special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "additional_special_tokens": [
+    "<brk>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78d0e717c77053f1c4b856d8661d9cb87c64f083a35418c087b9146300e4f585
+size 802397

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "en",
+  "sp_model_kwargs": {},
+  "target_lang": "fr",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

translation_no_trainer/1686747251.1500347/events.out.tfevents.1686747251.a100gpu3.3857623.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d8548ebd257c9e00bb04af5e051b943368d499a53d2d92a826b9e6ae940a0d7
+size 2243

translation_no_trainer/1686747251.2625148/hparams.yml

@@ -0,0 +1,43 @@
+checkpointing_steps: '1000'
+config_name: null
+context_size: 4
+context_word_dropout: 0.1
+dataset_config_name: sentences
+dataset_name: inseq/scat
+gradient_accumulation_steps: 1
+hub_model_id: context-mt/scat-marian-small-ctx4-cwd1-en-fr
+hub_token: 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
+ignore_pad_token_for_loss: true
+learning_rate: 5.0e-05
+logging_steps: '100'
+lr_scheduler_type: linear
+max_length: 128
+max_source_length: 512
+max_target_length: 128
+max_train_steps: 3470
+model_name_or_path: context-mt/iwslt17-marian-small-ctx4-cwd1-en-fr
+model_type: null
+num_beams: 5
+num_train_epochs: 5
+num_warmup_steps: 0
+output_dir: /scratch/p305238/scat-marian-small-ctx4-cwd1-en-fr
+overwrite_cache: false
+pad_to_max_length: true
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 16
+predict_with_generate: true
+preprocessing_num_workers: null
+push_to_hub: true
+report_to: tensorboard
+resume_from_checkpoint: null
+sample_context: true
+seed: null
+source_lang: en_XX
+target_lang: fr_XX
+tokenizer_name: null
+train_file: null
+use_slow_tokenizer: false
+val_max_target_length: null
+validation_file: null
+weight_decay: 0.0
+with_tracking: true

translation_no_trainer/events.out.tfevents.1686747251.a100gpu3.3857623.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:424ccf0c62051d746c9c63e93a5f5844583771ed21e65ee7f3d070a1609f0fe5
+size 1080