Training in progress, step 500

Files changed (16) hide show

.gitattributes CHANGED Viewed

@@ -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

 *.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 ADDED Viewed

	@@ -0,0 +1 @@


1	+ checkpoint-*/

config.json ADDED Viewed

+{
+  "_name_or_path": "facebook/mbart-large-50",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "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": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 250054
+}

pytorch_model.bin ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:11870ad860e8019aaf907bdfb61d48dd3eb337418418847c914cc7e4f2f6ba7e
+size 2444694045

runs/Mar05_17-14-27_499919ba898f/1678036548.1198778/events.out.tfevents.1678036548.499919ba898f.354.1 ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:dbe80a94144de8b8e07f99489f4c9a436d46d2612957947fc3bfc96ced55c3c5
+size 5917

runs/Mar05_17-14-27_499919ba898f/1678036580.7363493/events.out.tfevents.1678036580.499919ba898f.354.2 ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:363bbbe131eb082ac45feb64b70d57218756c7311ca43331cbdd9a569a120fdd
+size 5917

runs/Mar05_17-14-27_499919ba898f/1678036719.5416472/events.out.tfevents.1678036719.499919ba898f.354.3 ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:ccd72689e03c37ba14099ffc2a41a00adbbf8d0d9427fc13dfed60620a1e936e
+size 5917

runs/Mar05_17-14-27_499919ba898f/1678036755.938877/events.out.tfevents.1678036755.499919ba898f.354.4 ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:8445a2a03c32ec3b29bd5250f45e13506e7f880123f2ab96259e367792b89e52
+size 5917

runs/Mar05_17-14-27_499919ba898f/events.out.tfevents.1678036548.499919ba898f.354.0 ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:dad12e4ccaac2d919ef08aa67af67a0de08c6b2aa12fc74667e60a1d70135aac
+size 18664

runs/Mar05_17-22-10_499919ba898f/1678036967.9909241/events.out.tfevents.1678036967.499919ba898f.354.6 ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:bf3d6e6c94f7749326f79d9af4fdc4b8bc30f2dac74879e2d03a7726d97f2072
+size 5917

runs/Mar05_17-22-10_499919ba898f/events.out.tfevents.1678036967.499919ba898f.354.5 ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:4284c47393f5467c242c4b3979e4c554648de7670b90099c10d5129655003290
+size 4853

sentencepiece.bpe.model ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json ADDED Viewed

+{
+  "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>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:8d8611aadd832b6aa98f19d99a4f2d630f477cd2c3c0f1f6ff2f922c971916a7
+size 17109849

tokenizer_config.json ADDED Viewed

+{
+  "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>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1024,
+  "name_or_path": "facebook/mbart-large-50",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/suraj/projects/mbart-50/hf_models/mbart-50-large/special_tokens_map.json",
+  "src_lang": null,
+  "tgt_lang": null,
+  "tokenizer_class": "MBart50Tokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:b0bc5321b5945c9eaac76c535d9ef78be244a18e8268a9c1073c3952f187c158
+size 3643