add model files

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,173 @@
+{
+  "_name_or_path": "./drive/MyDrive/mbert2mbert/checkpoint-15000",
+  "architectures": [
+    "EncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "bert-base-multilingual-cased",
+    "add_cross_attention": true,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "directionality": "bidi",
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "pooler_fc_size": 768,
+    "pooler_num_attention_heads": 12,
+    "pooler_num_fc_layers": 3,
+    "pooler_size_per_head": 128,
+    "pooler_type": "first_token_transform",
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torchscript": false,
+    "transformers_version": "4.5.1",
+    "type_vocab_size": 2,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 119547
+  },
+  "decoder_start_token_id": 101,
+  "encoder": {
+    "_name_or_path": "bert-base-multilingual-cased",
+    "add_cross_attention": false,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "directionality": "bidi",
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "pooler_fc_size": 768,
+    "pooler_num_attention_heads": 12,
+    "pooler_num_fc_layers": 3,
+    "pooler_size_per_head": 128,
+    "pooler_type": "first_token_transform",
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torchscript": false,
+    "transformers_version": "4.5.1",
+    "type_vocab_size": 2,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 119547
+  },
+  "eos_token_id": 102,
+  "is_encoder_decoder": true,
+  "max_length": 42,
+  "min_length": 5,
+  "model_type": "encoder-decoder",
+  "pad_token_id": 0,
+  "tie_encoder_decoder": true,
+  "vocab_size": 119547
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6ff7ec04d79d8d46be651dbf957afccf1d7e7870b3cbd1f9f05c68763258edc
+size 827914229

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a43880977f4f83b4040c24bb11b6e5795e817a17a1668080851028cedc7b6fa
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/root/.cache/huggingface/transformers/46880f3b0081fda494a4e15b05787692aa4c1e21e0ff2428ba8b14d4eda0784d.b33e51591f94f17c238ee9b1fac75b96ff2678cbaed6e108feadb3449d18dc24", "name_or_path": "bert-base-multilingual-cased"}

trainer_state.json

@@ -0,0 +1,288 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.175986495041148,
+  "global_step": 17000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 4.4431,
+      "step": 1000
+    },
+    {
+      "epoch": 0.42,
+      "eval_loss": 3.1658337116241455,
+      "eval_rouge-1": 0.1104,
+      "eval_rouge-2": 0.0147,
+      "eval_rouge-l": 0.1071,
+      "eval_runtime": 938.5942,
+      "eval_samples_per_second": 4.447,
+      "step": 1000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 4.8873366381252815e-05,
+      "loss": 3.0017,
+      "step": 2000
+    },
+    {
+      "epoch": 0.84,
+      "eval_loss": 2.450249195098877,
+      "eval_rouge-1": 0.2256,
+      "eval_rouge-2": 0.0714,
+      "eval_rouge-l": 0.2134,
+      "eval_runtime": 828.0492,
+      "eval_samples_per_second": 5.041,
+      "step": 2000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 4.662009914375845e-05,
+      "loss": 2.258,
+      "step": 3000
+    },
+    {
+      "epoch": 1.27,
+      "eval_loss": 1.915558099746704,
+      "eval_rouge-1": 0.3442,
+      "eval_rouge-2": 0.1597,
+      "eval_rouge-l": 0.3284,
+      "eval_runtime": 854.823,
+      "eval_samples_per_second": 4.883,
+      "step": 3000
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 4.4366831906264086e-05,
+      "loss": 1.8476,
+      "step": 4000
+    },
+    {
+      "epoch": 1.69,
+      "eval_loss": 1.7214736938476562,
+      "eval_rouge-1": 0.3784,
+      "eval_rouge-2": 0.1998,
+      "eval_rouge-l": 0.362,
+      "eval_runtime": 711.98,
+      "eval_samples_per_second": 5.863,
+      "step": 4000
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 4.211356466876972e-05,
+      "loss": 1.6932,
+      "step": 5000
+    },
+    {
+      "epoch": 2.11,
+      "eval_loss": 1.6499994993209839,
+      "eval_rouge-1": 0.3992,
+      "eval_rouge-2": 0.2227,
+      "eval_rouge-l": 0.3822,
+      "eval_runtime": 721.767,
+      "eval_samples_per_second": 5.783,
+      "step": 5000
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 3.986029743127535e-05,
+      "loss": 1.5271,
+      "step": 6000
+    },
+    {
+      "epoch": 2.53,
+      "eval_loss": 1.5838263034820557,
+      "eval_rouge-1": 0.3999,
+      "eval_rouge-2": 0.2255,
+      "eval_rouge-l": 0.3825,
+      "eval_runtime": 791.7162,
+      "eval_samples_per_second": 5.272,
+      "step": 6000
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 3.760703019378098e-05,
+      "loss": 1.4984,
+      "step": 7000
+    },
+    {
+      "epoch": 2.95,
+      "eval_loss": 1.5331367254257202,
+      "eval_rouge-1": 0.4063,
+      "eval_rouge-2": 0.2319,
+      "eval_rouge-l": 0.39,
+      "eval_runtime": 787.263,
+      "eval_samples_per_second": 5.302,
+      "step": 7000
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 3.535376295628662e-05,
+      "loss": 1.3435,
+      "step": 8000
+    },
+    {
+      "epoch": 3.38,
+      "eval_loss": 1.5344029664993286,
+      "eval_rouge-1": 0.419,
+      "eval_rouge-2": 0.2391,
+      "eval_rouge-l": 0.4009,
+      "eval_runtime": 801.0657,
+      "eval_samples_per_second": 5.211,
+      "step": 8000
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 3.310049571879225e-05,
+      "loss": 1.275,
+      "step": 9000
+    },
+    {
+      "epoch": 3.8,
+      "eval_loss": 1.5167639255523682,
+      "eval_rouge-1": 0.4172,
+      "eval_rouge-2": 0.2399,
+      "eval_rouge-l": 0.398,
+      "eval_runtime": 714.2604,
+      "eval_samples_per_second": 5.844,
+      "step": 9000
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 3.0847228481297885e-05,
+      "loss": 1.2267,
+      "step": 10000
+    },
+    {
+      "epoch": 4.22,
+      "eval_loss": 1.5133156776428223,
+      "eval_rouge-1": 0.4215,
+      "eval_rouge-2": 0.2435,
+      "eval_rouge-l": 0.402,
+      "eval_runtime": 712.9933,
+      "eval_samples_per_second": 5.854,
+      "step": 10000
+    },
+    {
+      "epoch": 4.64,
+      "learning_rate": 2.859396124380352e-05,
+      "loss": 1.1519,
+      "step": 11000
+    },
+    {
+      "epoch": 4.64,
+      "eval_loss": 1.4870655536651611,
+      "eval_rouge-1": 0.4202,
+      "eval_rouge-2": 0.244,
+      "eval_rouge-l": 0.4013,
+      "eval_runtime": 437.1167,
+      "eval_samples_per_second": 9.549,
+      "step": 11000
+    },
+    {
+      "epoch": 5.07,
+      "learning_rate": 2.6340694006309152e-05,
+      "loss": 1.1841,
+      "step": 12000
+    },
+    {
+      "epoch": 5.07,
+      "eval_loss": 1.5044740438461304,
+      "eval_rouge-1": 0.4269,
+      "eval_rouge-2": 0.2471,
+      "eval_rouge-l": 0.4076,
+      "eval_runtime": 446.0452,
+      "eval_samples_per_second": 9.358,
+      "step": 12000
+    },
+    {
+      "epoch": 5.49,
+      "learning_rate": 2.4087426768814784e-05,
+      "loss": 1.0586,
+      "step": 13000
+    },
+    {
+      "epoch": 5.49,
+      "eval_loss": 1.4930425882339478,
+      "eval_rouge-1": 0.4285,
+      "eval_rouge-2": 0.2518,
+      "eval_rouge-l": 0.4109,
+      "eval_runtime": 430.9672,
+      "eval_samples_per_second": 9.685,
+      "step": 13000
+    },
+    {
+      "epoch": 5.91,
+      "learning_rate": 2.1834159531320416e-05,
+      "loss": 1.0657,
+      "step": 14000
+    },
+    {
+      "epoch": 5.91,
+      "eval_loss": 1.488339900970459,
+      "eval_rouge-1": 0.4273,
+      "eval_rouge-2": 0.2514,
+      "eval_rouge-l": 0.4084,
+      "eval_runtime": 438.2586,
+      "eval_samples_per_second": 9.524,
+      "step": 14000
+    },
+    {
+      "epoch": 6.33,
+      "learning_rate": 1.958089229382605e-05,
+      "loss": 0.9725,
+      "step": 15000
+    },
+    {
+      "epoch": 6.33,
+      "eval_loss": 1.5135878324508667,
+      "eval_rouge-1": 0.4312,
+      "eval_rouge-2": 0.2537,
+      "eval_rouge-l": 0.4116,
+      "eval_runtime": 436.2911,
+      "eval_samples_per_second": 9.567,
+      "step": 15000
+    },
+    {
+      "epoch": 6.75,
+      "learning_rate": 1.732762505633168e-05,
+      "loss": 0.9176,
+      "step": 16000
+    },
+    {
+      "epoch": 6.75,
+      "eval_loss": 1.5166784524917603,
+      "eval_rouge-1": 0.433,
+      "eval_rouge-2": 0.2559,
+      "eval_rouge-l": 0.4146,
+      "eval_runtime": 820.6736,
+      "eval_samples_per_second": 5.086,
+      "step": 16000
+    },
+    {
+      "epoch": 7.18,
+      "learning_rate": 1.5074357818837314e-05,
+      "loss": 0.8982,
+      "step": 17000
+    },
+    {
+      "epoch": 7.18,
+      "eval_loss": 1.535448431968689,
+      "eval_rouge-1": 0.4293,
+      "eval_rouge-2": 0.2538,
+      "eval_rouge-l": 0.4101,
+      "eval_runtime": 828.443,
+      "eval_samples_per_second": 5.038,
+      "step": 17000
+    }
+  ],
+  "max_steps": 23690,
+  "num_train_epochs": 10,
+  "total_flos": 1.317233087652327e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63d31c04276cc71b7fce380bad6f43829c17562ecc7ae01678dcf34351c5526a
+size 2415