Training in progress epoch 0

.gitattributes

@@ -32,3 +32,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.gitignore

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

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<brk>": 250054
+}

config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "context-mt/iwslt17-mbart50-1toM-ctx4-cwd1-en-fr",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "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": 200,
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "normalize_before": true,
+  "normalize_embedding": true,
+  "num_beams": 5,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "tokenizer_class": "MBart50Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "use_cache": true,
+  "vocab_size": 250055
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "max_length": 200,
+  "num_beams": 5,
+  "pad_token_id": 1,
+  "transformers_version": "4.28.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5e343836fc2dea823621f3371357c6c6a7e428e20a0b157d264832080900752
+size 2444698141

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,70 @@
+{
+  "additional_special_tokens": [
+    "ar_AR",
+    "cs_CZ",
+    "de_DE",
+    "en_XX",
+    "es_XX",
+    "et_EE",
+    "fi_FI",
+    "fr_XX",
+    "gu_IN",
+    "hi_IN",
+    "it_IT",
+    "ja_XX",
+    "kk_KZ",
+    "ko_KR",
+    "lt_LT",
+    "lv_LV",
+    "my_MM",
+    "ne_NP",
+    "nl_XX",
+    "ro_RO",
+    "ru_RU",
+    "si_LK",
+    "tr_TR",
+    "vi_VN",
+    "zh_CN",
+    "af_ZA",
+    "az_AZ",
+    "bn_IN",
+    "fa_IR",
+    "he_IL",
+    "hr_HR",
+    "id_ID",
+    "ka_GE",
+    "km_KH",
+    "mk_MK",
+    "ml_IN",
+    "mn_MN",
+    "mr_IN",
+    "pl_PL",
+    "ps_AF",
+    "pt_XX",
+    "sv_SE",
+    "sw_KE",
+    "ta_IN",
+    "te_IN",
+    "th_TH",
+    "tl_XX",
+    "uk_UA",
+    "ur_PK",
+    "xh_ZA",
+    "gl_ES",
+    "sl_SI",
+    "<brk>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:520f9abb55798ab4a7884be3c69b3d6b97994befcb06ccd4557517541bdd90ce
+size 17094846

tokenizer_config.json

@@ -0,0 +1,77 @@
+{
+  "additional_special_tokens": [
+    "ar_AR",
+    "cs_CZ",
+    "de_DE",
+    "en_XX",
+    "es_XX",
+    "et_EE",
+    "fi_FI",
+    "fr_XX",
+    "gu_IN",
+    "hi_IN",
+    "it_IT",
+    "ja_XX",
+    "kk_KZ",
+    "ko_KR",
+    "lt_LT",
+    "lv_LV",
+    "my_MM",
+    "ne_NP",
+    "nl_XX",
+    "ro_RO",
+    "ru_RU",
+    "si_LK",
+    "tr_TR",
+    "vi_VN",
+    "zh_CN",
+    "af_ZA",
+    "az_AZ",
+    "bn_IN",
+    "fa_IR",
+    "he_IL",
+    "hr_HR",
+    "id_ID",
+    "ka_GE",
+    "km_KH",
+    "mk_MK",
+    "ml_IN",
+    "mn_MN",
+    "mr_IN",
+    "pl_PL",
+    "ps_AF",
+    "pt_XX",
+    "sv_SE",
+    "sw_KE",
+    "ta_IN",
+    "te_IN",
+    "th_TH",
+    "tl_XX",
+    "uk_UA",
+    "ur_PK",
+    "xh_ZA",
+    "gl_ES",
+    "sl_SI"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "language_codes": "ML50",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "src_lang": null,
+  "tgt_lang": null,
+  "tokenizer_class": "MBart50Tokenizer",
+  "unk_token": "<unk>"
+}

translation_no_trainer/1686823411.2819154/events.out.tfevents.1686823411.a100gpu1.2346251.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c0cc6de12e8b31226bd1c3117195ad980663d80d4bf7f09a22086a00c223d9f
+size 2243

translation_no_trainer/1686823411.313841/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: 2
+hub_model_id: context-mt/scat-mbart50-1toM-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: 6935
+model_name_or_path: context-mt/iwslt17-mbart50-1toM-ctx4-cwd1-en-fr
+model_type: null
+num_beams: 5
+num_train_epochs: 5
+num_warmup_steps: 0
+output_dir: /scratch/p305238/scat-mbart50-1toM-ctx4-cwd1-en-fr
+overwrite_cache: false
+pad_to_max_length: true
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 4
+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.1686823411.a100gpu1.2346251.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f001418cc5ff4dafd3fa1b4e47df945c248ae9d0386bfe4e36df5549cf6b61
+size 3797