Upload 8 files

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "Turkish-NLP/t5-efficient-base-turkish",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 36,
+  "num_heads": 12,
+  "num_layers": 36,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.4"
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:269dbf2213fadf2fab87d4e6cb9754109bbb43bf28ee2ee952a420ea0870b34f
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b097d732cba2ad47b9977234e3349f0a6ee2c416c7a8fb6f99d6ff0b3dd99027
+size 1064

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ca0ade8cf006bd16c9d7dafebce0f7fad8ba4018f3e70947e972cf10a2b3b03
+size 839200

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "special_tokens_map_file": null, "name_or_path": "./", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}

trainer_state.json

@@ -0,0 +1,275 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 15010,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1665556295802798,
+      "grad_norm": 1.6862213611602783,
+      "learning_rate": 0.00048334443704197203,
+      "loss": 2.122,
+      "step": 500
+    },
+    {
+      "epoch": 0.3331112591605596,
+      "grad_norm": 0.9895781874656677,
+      "learning_rate": 0.00046668887408394405,
+      "loss": 1.6754,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4996668887408394,
+      "grad_norm": 1.4011154174804688,
+      "learning_rate": 0.00045003331112591607,
+      "loss": 1.5258,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6662225183211192,
+      "grad_norm": 1.263901948928833,
+      "learning_rate": 0.0004333777481678881,
+      "loss": 1.3949,
+      "step": 2000
+    },
+    {
+      "epoch": 0.832778147901399,
+      "grad_norm": 0.9926736354827881,
+      "learning_rate": 0.0004167221852098601,
+      "loss": 1.323,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9993337774816788,
+      "grad_norm": 1.2104265689849854,
+      "learning_rate": 0.0004000666222518321,
+      "loss": 1.2978,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.1156065464019775,
+      "eval_runtime": 37.2553,
+      "eval_samples_per_second": 80.579,
+      "eval_steps_per_second": 10.093,
+      "step": 3002
+    },
+    {
+      "epoch": 1.1658894070619588,
+      "grad_norm": 0.9220499992370605,
+      "learning_rate": 0.00038341105929380414,
+      "loss": 0.964,
+      "step": 3500
+    },
+    {
+      "epoch": 1.3324450366422385,
+      "grad_norm": 1.2684720754623413,
+      "learning_rate": 0.00036675549633577616,
+      "loss": 0.9784,
+      "step": 4000
+    },
+    {
+      "epoch": 1.4990006662225184,
+      "grad_norm": 1.3914306163787842,
+      "learning_rate": 0.0003500999333777481,
+      "loss": 0.9265,
+      "step": 4500
+    },
+    {
+      "epoch": 1.6655562958027983,
+      "grad_norm": 1.0393187999725342,
+      "learning_rate": 0.0003334443704197202,
+      "loss": 0.9401,
+      "step": 5000
+    },
+    {
+      "epoch": 1.832111925383078,
+      "grad_norm": 1.1595275402069092,
+      "learning_rate": 0.0003167888074616922,
+      "loss": 0.9091,
+      "step": 5500
+    },
+    {
+      "epoch": 1.9986675549633577,
+      "grad_norm": 1.2401949167251587,
+      "learning_rate": 0.00030013324450366423,
+      "loss": 0.9271,
+      "step": 6000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.9488099217414856,
+      "eval_runtime": 37.415,
+      "eval_samples_per_second": 80.235,
+      "eval_steps_per_second": 10.049,
+      "step": 6004
+    },
+    {
+      "epoch": 2.1652231845436374,
+      "grad_norm": 0.6324372887611389,
+      "learning_rate": 0.00028347768154563625,
+      "loss": 0.6576,
+      "step": 6500
+    },
+    {
+      "epoch": 2.3317788141239175,
+      "grad_norm": 1.377943992614746,
+      "learning_rate": 0.00026682211858760827,
+      "loss": 0.6499,
+      "step": 7000
+    },
+    {
+      "epoch": 2.498334443704197,
+      "grad_norm": 0.9929794669151306,
+      "learning_rate": 0.0002501665556295803,
+      "loss": 0.6509,
+      "step": 7500
+    },
+    {
+      "epoch": 2.664890073284477,
+      "grad_norm": 1.331009030342102,
+      "learning_rate": 0.0002335109926715523,
+      "loss": 0.6492,
+      "step": 8000
+    },
+    {
+      "epoch": 2.831445702864757,
+      "grad_norm": 0.9260538816452026,
+      "learning_rate": 0.00021685542971352432,
+      "loss": 0.6765,
+      "step": 8500
+    },
+    {
+      "epoch": 2.9980013324450367,
+      "grad_norm": 1.6844342947006226,
+      "learning_rate": 0.00020019986675549634,
+      "loss": 0.6452,
+      "step": 9000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.9022971391677856,
+      "eval_runtime": 37.548,
+      "eval_samples_per_second": 79.951,
+      "eval_steps_per_second": 10.014,
+      "step": 9006
+    },
+    {
+      "epoch": 3.1645569620253164,
+      "grad_norm": 0.6371086835861206,
+      "learning_rate": 0.00018354430379746836,
+      "loss": 0.4646,
+      "step": 9500
+    },
+    {
+      "epoch": 3.331112591605596,
+      "grad_norm": 1.005698323249817,
+      "learning_rate": 0.00016688874083944038,
+      "loss": 0.4706,
+      "step": 10000
+    },
+    {
+      "epoch": 3.497668221185876,
+      "grad_norm": 0.990774393081665,
+      "learning_rate": 0.0001502331778814124,
+      "loss": 0.434,
+      "step": 10500
+    },
+    {
+      "epoch": 3.664223850766156,
+      "grad_norm": 0.7444645762443542,
+      "learning_rate": 0.00013357761492338441,
+      "loss": 0.4682,
+      "step": 11000
+    },
+    {
+      "epoch": 3.8307794803464357,
+      "grad_norm": 1.1938289403915405,
+      "learning_rate": 0.00011692205196535643,
+      "loss": 0.4428,
+      "step": 11500
+    },
+    {
+      "epoch": 3.9973351099267154,
+      "grad_norm": 1.2232627868652344,
+      "learning_rate": 0.00010026648900732845,
+      "loss": 0.4446,
+      "step": 12000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.9124976396560669,
+      "eval_runtime": 37.6584,
+      "eval_samples_per_second": 79.717,
+      "eval_steps_per_second": 9.985,
+      "step": 12008
+    },
+    {
+      "epoch": 4.1638907395069955,
+      "grad_norm": 1.035305380821228,
+      "learning_rate": 8.361092604930047e-05,
+      "loss": 0.3292,
+      "step": 12500
+    },
+    {
+      "epoch": 4.330446369087275,
+      "grad_norm": 1.409875512123108,
+      "learning_rate": 6.695536309127249e-05,
+      "loss": 0.321,
+      "step": 13000
+    },
+    {
+      "epoch": 4.497001998667555,
+      "grad_norm": 1.468259334564209,
+      "learning_rate": 5.0299800133244506e-05,
+      "loss": 0.3161,
+      "step": 13500
+    },
+    {
+      "epoch": 4.663557628247835,
+      "grad_norm": 1.00761878490448,
+      "learning_rate": 3.3644237175216524e-05,
+      "loss": 0.3214,
+      "step": 14000
+    },
+    {
+      "epoch": 4.830113257828114,
+      "grad_norm": 0.7190210223197937,
+      "learning_rate": 1.698867421718854e-05,
+      "loss": 0.3037,
+      "step": 14500
+    },
+    {
+      "epoch": 4.996668887408394,
+      "grad_norm": 0.6449595093727112,
+      "learning_rate": 3.3311125916055966e-07,
+      "loss": 0.3045,
+      "step": 15000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 15010,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 10000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6083104659545088.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc3740d66ce7f13a9bf52c0f372ab07710a244dec0c4cce502fad110e30edb3
+size 5048