Training in progress, step 3500

checkpoint-3500/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-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf8d08aca78f489e163c93e5054239f62f1f094f684c8170a4411ee6ecbb6110
+size 109498141

checkpoint-3500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42bc267ec3f47ed324eaea3e80c3555a90a16167ee72507bc0e7b1fa0ce69f09
+size 54776045

checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c0ef0e7a1ec7304bab999a64193c6d2d776eb7af9363b6eedd08102f17139f1
+size 14503

checkpoint-3500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcba4a84c340116e7a0518ad0be03f63e6abff14ff54ab92d49f35749e23a5be
+size 623

checkpoint-3500/special_tokens_map.json

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

checkpoint-3500/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-3500/trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.847645429362881,
+  "global_step": 3500,
+  "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
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.348456859588623,
+      "eval_runtime": 7.0052,
+      "eval_samples_per_second": 206.561,
+      "eval_steps_per_second": 12.99,
+      "step": 2166
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 8.457987072945522e-06,
+      "loss": 2.4214,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.0450046062469482,
+      "eval_runtime": 6.9443,
+      "eval_samples_per_second": 208.371,
+      "eval_steps_per_second": 13.104,
+      "step": 2888
+    },
+    {
+      "epoch": 4.16,
+      "learning_rate": 6.1495844875346266e-06,
+      "loss": 2.2208,
+      "step": 3000
+    },
+    {
+      "epoch": 4.85,
+      "learning_rate": 3.841181902123731e-06,
+      "loss": 2.1568,
+      "step": 3500
+    }
+  ],
+  "max_steps": 4332,
+  "num_train_epochs": 6,
+  "total_flos": 1226347294685184.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3500/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 sha256:2a0af67201568179f1a046bb2b7363fe446662f1fceeea5849921001b6523d54
+oid sha256:42bc267ec3f47ed324eaea3e80c3555a90a16167ee72507bc0e7b1fa0ce69f09
 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 sha256:51e3ce9197a7573e2372e0ad0e2f8fb97714040b309fbc09d1c014b9bee6ef4a
-size 5703
+oid sha256:073d0adc83c0253d5eb894bc7d8632fe2966f8fbe9984c15841a1ff14d7af1d6
+size 5860