Training in progress, step 2000

checkpoint-2000/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "loodos/electra-small-turkish-uncased-discriminator",
+  "architectures": [
+    "ElectraForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:210feb794d6c32596b7d4c58bf562414b9c350744da7a591b465da4c96a37585
+size 109498141

checkpoint-2000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fb417fa220b162eb67dfc71854c62998ec52642664d5ab725a9d3a6f163073f
+size 54776045

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f5c13898f322b872f7eff156b8263ba00612ba532ab0f3a934aa6aab3941c9d
+size 14503

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd26edfc0dc425d9d08064e32a4295f509680936eeed61163af09e34bc5a5a2a
+size 623

checkpoint-2000/special_tokens_map.json

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

checkpoint-2000/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "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": "/root/.cache/huggingface/transformers/444866c6552ed3ad4574d4ea6433149e5e30eef747074cfa66be2388dadf2646.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "loodos/electra-small-turkish-uncased-discriminator", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "ElectraTokenizer"}

checkpoint-2000/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.770083102493075,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.7691597414589106e-05,
+      "loss": 4.128,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.7186717987060547,
+      "eval_runtime": 6.8658,
+      "eval_samples_per_second": 210.754,
+      "eval_steps_per_second": 13.254,
+      "step": 722
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.538319482917821e-05,
+      "loss": 3.0376,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.448554039001465,
+      "eval_runtime": 6.9162,
+      "eval_samples_per_second": 209.22,
+      "eval_steps_per_second": 13.158,
+      "step": 1444
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 1.3074792243767314e-05,
+      "loss": 2.7618,
+      "step": 1500
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 1.0766389658356418e-05,
+      "loss": 2.5304,
+      "step": 2000
+    }
+  ],
+  "max_steps": 4332,
+  "num_train_epochs": 6,
+  "total_flos": 700826230766592.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f59f77975d8e31159a76d6f258f7fb03c99048c15d507345621a56c397d0996
+size 3247

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae0f8edfc1f8b05ea12819dcf9fd61e4bc9d1a056c15f7e49fbba81fc4f743e1
+oid sha256:8fb417fa220b162eb67dfc71854c62998ec52642664d5ab725a9d3a6f163073f
 size 54776045

runs/Jan15_05-37-52_b97e1d8ba7c6/events.out.tfevents.1642225094.b97e1d8ba7c6.72.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26fb4d62b96e3838bfe6c579f1f75c8d9d287ed7c2093958ee737ea294e156ca
-size 4690
+oid sha256:24ee5c122ceaf45edaf328b66161c57fc9f38878e7ff50a51af97a7f0798e10c
+size 4847