Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "husnu/bert-base-turkish-128k-cased-finetuned_lr-2e-05_epochs-3",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 128000
+}

last-checkpoint/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "husnu/bert-base-turkish-128k-cased-finetuned_lr-2e-05_epochs-3",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 128000
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a65e03cab858782e5135a131160b406b098b1490134ae5d549977519a14bcb9
+size 1470165733

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb1318d09fbb0e6af7f5711ac08fdca3e2cc4c123b73a989a6db5a1c6650960a
+size 735108529

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea243a68bf7e14720486d113eeaa790fb5610e6149ee0c92efb6653782e7dcb2
+size 14503

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0699c175215d5ef6b36767b96735dc5c137c9be952fcbd0bc4ec0142c9f3ee5a
+size 623

last-checkpoint/special_tokens_map.json

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

last-checkpoint/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": "husnu/bert-base-turkish-128k-cased-finetuned_lr-2e-05_epochs-3", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}

last-checkpoint/trainer_state.json

@@ -0,0 +1,22 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.22271714922049,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8515219005196734e-05,
+      "loss": 0.7275,
+      "step": 500
+    }
+  ],
+  "max_steps": 6735,
+  "num_train_epochs": 3,
+  "total_flos": 783890270208000.0,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e08b6468ef00f8a32f494483e432a6fed59f9c23b2b5a8ae2ad65dcde0ea601f
+size 3183

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb1318d09fbb0e6af7f5711ac08fdca3e2cc4c123b73a989a6db5a1c6650960a
+size 735108529

runs/Jan15_16-54-07_a78d8ddf8d3b/1642265704.7615817/events.out.tfevents.1642265704.a78d8ddf8d3b.72.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1deed6675180f335b5fde7166186e484fdd88d2c8d3c5b22af3efc6e5912ca0
+size 4979

runs/Jan15_16-54-07_a78d8ddf8d3b/events.out.tfevents.1642265704.a78d8ddf8d3b.72.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1c15b8fd97615f1da244a9df77bcb402d7226bcbb82ca28b69161db3c8bc726
+size 3727

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": "husnu/bert-base-turkish-128k-cased-finetuned_lr-2e-05_epochs-3", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e08b6468ef00f8a32f494483e432a6fed59f9c23b2b5a8ae2ad65dcde0ea601f
+size 3183