Initial commit from mrm8488

config.json

@@ -0,0 +1,167 @@
+{
+  "architectures": [
+    "EncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "bert-base-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,
+    "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,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": 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": "4.6.0.dev0",
+    "type_vocab_size": 2,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 28996
+  },
+  "decoder_start_token_id": 101,
+  "early_stopping": true,
+  "encoder": {
+    "_name_or_path": "bert-base-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,
+    "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,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": 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": "4.6.0.dev0",
+    "type_vocab_size": 2,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 28996
+  },
+  "eos_token_id": 102,
+  "is_encoder_decoder": true,
+  "length_penalty": 2.0,
+  "max_length": 64,
+  "min_length": 4,
+  "model_type": "encoder-decoder",
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 0,
+  "tie_encoder_decoder": true,
+  "transformers_version": null,
+  "vocab_size": 28996
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fc523422a33b037fd11530cf3dea839f6874d07aa8348cf75465aac3905ab3f
+size 549391205

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, "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, "name_or_path": "bert-base-cased"}

trainer_state.json

@@ -0,0 +1,298 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.795748228428511,
+  "global_step": 23500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.8957899124635265e-05,
+      "loss": 4.6229,
+      "step": 500
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.7915798249270535e-05,
+      "loss": 3.8572,
+      "step": 1000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.68736973739058e-05,
+      "loss": 3.574,
+      "step": 1500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 4.583159649854106e-05,
+      "loss": 3.2686,
+      "step": 2000
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 4.4789495623176324e-05,
+      "loss": 3.0761,
+      "step": 2500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 4.374739474781159e-05,
+      "loss": 2.8529,
+      "step": 3000
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 4.2705293872446856e-05,
+      "loss": 2.8138,
+      "step": 3500
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 4.166319299708212e-05,
+      "loss": 2.7723,
+      "step": 4000
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 4.062109212171739e-05,
+      "loss": 2.7547,
+      "step": 4500
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 3.9578991246352645e-05,
+      "loss": 2.6349,
+      "step": 5000
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 3.8536890370987915e-05,
+      "loss": 2.5105,
+      "step": 5500
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 3.749478949562318e-05,
+      "loss": 2.4989,
+      "step": 6000
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 3.645268862025844e-05,
+      "loss": 2.509,
+      "step": 6500
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 3.541058774489371e-05,
+      "loss": 2.5043,
+      "step": 7000
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 3.436848686952897e-05,
+      "loss": 2.3714,
+      "step": 7500
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 3.3326385994164236e-05,
+      "loss": 2.3006,
+      "step": 8000
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 3.22842851187995e-05,
+      "loss": 2.3216,
+      "step": 8500
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 3.124218424343476e-05,
+      "loss": 2.3245,
+      "step": 9000
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 3.020008336807003e-05,
+      "loss": 2.3094,
+      "step": 9500
+    },
+    {
+      "epoch": 4.17,
+      "learning_rate": 2.9157982492705294e-05,
+      "loss": 2.1743,
+      "step": 10000
+    },
+    {
+      "epoch": 4.38,
+      "learning_rate": 2.811588161734056e-05,
+      "loss": 2.1446,
+      "step": 10500
+    },
+    {
+      "epoch": 4.59,
+      "learning_rate": 2.7073780741975824e-05,
+      "loss": 2.1617,
+      "step": 11000
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 2.6031679866611093e-05,
+      "loss": 2.1707,
+      "step": 11500
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.4989578991246353e-05,
+      "loss": 2.1719,
+      "step": 12000
+    },
+    {
+      "epoch": 5.21,
+      "learning_rate": 2.394747811588162e-05,
+      "loss": 2.0137,
+      "step": 12500
+    },
+    {
+      "epoch": 5.42,
+      "learning_rate": 2.2905377240516885e-05,
+      "loss": 2.0293,
+      "step": 13000
+    },
+    {
+      "epoch": 5.63,
+      "learning_rate": 2.1863276365152145e-05,
+      "loss": 2.0414,
+      "step": 13500
+    },
+    {
+      "epoch": 5.84,
+      "learning_rate": 2.082117548978741e-05,
+      "loss": 2.032,
+      "step": 14000
+    },
+    {
+      "epoch": 6.04,
+      "learning_rate": 1.9779074614422678e-05,
+      "loss": 2.009,
+      "step": 14500
+    },
+    {
+      "epoch": 6.25,
+      "learning_rate": 1.873697373905794e-05,
+      "loss": 1.9163,
+      "step": 15000
+    },
+    {
+      "epoch": 6.46,
+      "learning_rate": 1.7694872863693207e-05,
+      "loss": 1.9179,
+      "step": 15500
+    },
+    {
+      "epoch": 6.67,
+      "learning_rate": 1.6652771988328473e-05,
+      "loss": 1.9323,
+      "step": 16000
+    },
+    {
+      "epoch": 6.88,
+      "learning_rate": 1.5610671112963736e-05,
+      "loss": 1.9234,
+      "step": 16500
+    },
+    {
+      "epoch": 7.09,
+      "learning_rate": 1.4568570237598999e-05,
+      "loss": 1.8964,
+      "step": 17000
+    },
+    {
+      "epoch": 7.29,
+      "learning_rate": 1.3526469362234265e-05,
+      "loss": 1.8314,
+      "step": 17500
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 1.248436848686953e-05,
+      "loss": 1.8313,
+      "step": 18000
+    },
+    {
+      "epoch": 7.71,
+      "learning_rate": 1.1442267611504794e-05,
+      "loss": 1.8317,
+      "step": 18500
+    },
+    {
+      "epoch": 7.92,
+      "learning_rate": 1.0400166736140059e-05,
+      "loss": 1.8431,
+      "step": 19000
+    },
+    {
+      "epoch": 8.13,
+      "learning_rate": 9.358065860775324e-06,
+      "loss": 1.791,
+      "step": 19500
+    },
+    {
+      "epoch": 8.34,
+      "learning_rate": 8.315964985410588e-06,
+      "loss": 1.7665,
+      "step": 20000
+    },
+    {
+      "epoch": 8.55,
+      "learning_rate": 7.273864110045853e-06,
+      "loss": 1.7617,
+      "step": 20500
+    },
+    {
+      "epoch": 8.75,
+      "learning_rate": 6.2317632346811174e-06,
+      "loss": 1.7643,
+      "step": 21000
+    },
+    {
+      "epoch": 8.96,
+      "learning_rate": 5.189662359316382e-06,
+      "loss": 1.7838,
+      "step": 21500
+    },
+    {
+      "epoch": 9.17,
+      "learning_rate": 4.147561483951647e-06,
+      "loss": 1.722,
+      "step": 22000
+    },
+    {
+      "epoch": 9.38,
+      "learning_rate": 3.1054606085869112e-06,
+      "loss": 1.7245,
+      "step": 22500
+    },
+    {
+      "epoch": 9.59,
+      "learning_rate": 2.0633597332221763e-06,
+      "loss": 1.7171,
+      "step": 23000
+    },
+    {
+      "epoch": 9.8,
+      "learning_rate": 1.0212588578574407e-06,
+      "loss": 1.7165,
+      "step": 23500
+    }
+  ],
+  "max_steps": 23990,
+  "num_train_epochs": 10,
+  "total_flos": 1687120822272000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a22b8ae2d392ffe6efdf465e7a497a28d3890f83573f0f1c66a94e063f945bec
+size 2543