hello

config.json

@@ -0,0 +1,153 @@
+{
+  "architectures": [
+    "EncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "dbmdz/bert-base-turkish-cased",
+    "add_cross_attention": true,
+    "architectures": null,
+    "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,
+    "eos_token_id": null,
+    "finetuning_task": 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,
+    "pruned_heads": {},
+    "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": "4.2.1",
+    "type_vocab_size": 2,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32000,
+    "xla_device": null
+  },
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "encoder": {
+    "_name_or_path": "dbmdz/bert-base-turkish-cased",
+    "add_cross_attention": false,
+    "architectures": null,
+    "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,
+    "eos_token_id": null,
+    "finetuning_task": 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,
+    "pruned_heads": {},
+    "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": "4.2.1",
+    "type_vocab_size": 2,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32000,
+    "xla_device": null
+  },
+  "eos_token_id": 3,
+  "is_encoder_decoder": true,
+  "length_penalty": 2.0,
+  "max_length": 40,
+  "min_length": 5,
+  "model_type": "encoder-decoder",
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 0,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0dd1e2d71e2d4836d10b3dc5d443ff5732b3e2febb870bf742770b5773d3b9f
+size 998772891

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, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "dbmdz/bert-base-turkish-cased", "do_basic_tokenize": true, "never_split": null}

trainer_state.json

@@ -0,0 +1,184 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 11580,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.784110535405873e-05,
+      "loss": 4.4347,
+      "step": 500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.5682210708117445e-05,
+      "loss": 3.0223,
+      "step": 1000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.352331606217617e-05,
+      "loss": 2.5837,
+      "step": 1500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.136442141623489e-05,
+      "loss": 2.3595,
+      "step": 2000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.920552677029361e-05,
+      "loss": 2.225,
+      "step": 2500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.704663212435233e-05,
+      "loss": 2.0827,
+      "step": 3000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.4887737478411055e-05,
+      "loss": 1.9716,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.879624843597412,
+      "eval_rouge2_fmeasure": 0.2999,
+      "eval_rouge2_precision": 0.326,
+      "eval_rouge2_recall": 0.2944,
+      "eval_runtime": 57.7084,
+      "eval_samples_per_second": 20.794,
+      "step": 3860
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 3.272884283246977e-05,
+      "loss": 1.8231,
+      "step": 4000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.05699481865285e-05,
+      "loss": 1.5489,
+      "step": 4500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 2.841105354058722e-05,
+      "loss": 1.5264,
+      "step": 5000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 2.6252158894645944e-05,
+      "loss": 1.5027,
+      "step": 5500
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.4093264248704665e-05,
+      "loss": 1.4792,
+      "step": 6000
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 2.1934369602763387e-05,
+      "loss": 1.4515,
+      "step": 6500
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.9775474956822108e-05,
+      "loss": 1.4273,
+      "step": 7000
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.761658031088083e-05,
+      "loss": 1.418,
+      "step": 7500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.6983058452606201,
+      "eval_rouge2_fmeasure": 0.3188,
+      "eval_rouge2_precision": 0.3398,
+      "eval_rouge2_recall": 0.3172,
+      "eval_runtime": 59.4641,
+      "eval_samples_per_second": 20.18,
+      "step": 7720
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 1.5457685664939554e-05,
+      "loss": 1.2305,
+      "step": 8000
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 1.3298791018998274e-05,
+      "loss": 1.0815,
+      "step": 8500
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 1.1139896373056995e-05,
+      "loss": 1.1018,
+      "step": 9000
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 8.981001727115718e-06,
+      "loss": 1.0829,
+      "step": 9500
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 6.822107081174439e-06,
+      "loss": 1.0609,
+      "step": 10000
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.663212435233161e-06,
+      "loss": 1.0557,
+      "step": 10500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 2.504317789291883e-06,
+      "loss": 1.0546,
+      "step": 11000
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 3.454231433506045e-07,
+      "loss": 1.0538,
+      "step": 11500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.6779444217681885,
+      "eval_rouge2_fmeasure": 0.3222,
+      "eval_rouge2_precision": 0.3433,
+      "eval_rouge2_recall": 0.3198,
+      "eval_runtime": 60.5062,
+      "eval_samples_per_second": 19.833,
+      "step": 11580
+    }
+  ],
+  "max_steps": 11580,
+  "num_train_epochs": 3,
+  "total_flos": 22201145347276800,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e08e28a607a0b2658a37c9a61d346308cc2abafe1dd07b3a55b42ac912181d8
+size 2095