initial commit

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "kravchenko/uk-mt5-large",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 2816,
+  "d_kv": 64,
+  "d_model": 1024,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "mt5",
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.4",
+  "use_cache": false,
+  "vocab_size": 30000
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ed994b4fa401740d248fec34fe4a852ceb764d50aff89a7bfe16d935d90e88
+size 5755849

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5fad91a0aa847e04d547f1c78f73d58e14245d5ea39fe08691dc317bdec8964
+size 3115357157

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf94df6171928ef3f5e9c61c8ef690e0ac50801ca136c847c1dc73ee0580900
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0b3bedfe869f037fae69543e3c43cf32ea2628383517cb0fe8a3b7ea89b1604
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa8ea53d190098f2632bd1c44b62731a90a9257a96081183c1a361a24f7ea8ff
+size 804017

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "sp_model_kwargs": {}, "special_tokens_map_file": "/root/.cache/huggingface/transformers/185abfb2369e8865a1629919f3937e6f094d5c5e4629c003bb05efae92ee060a.294ebaa4cd17bb284635004c92d2c4d522ec488c828dcce0c2471b6f28e3fe82", "name_or_path": "kravchenko/uk-mt5-large", "tokenizer_class": "T5Tokenizer"}

trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.23396648466587067,
+  "best_model_checkpoint": "uk-mt5-small-gec/checkpoint-400",
+  "epoch": 1.5209125475285172,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0008479087452471484,
+      "loss": 0.8294,
+      "step": 200
+    },
+    {
+      "epoch": 0.76,
+      "eval_google_bleu": 0.4205046652337586,
+      "eval_loss": 0.24924862384796143,
+      "eval_runtime": 330.8079,
+      "eval_samples_per_second": 5.653,
+      "eval_steps_per_second": 0.354,
+      "step": 200
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.0006958174904942966,
+      "loss": 0.2123,
+      "step": 400
+    },
+    {
+      "epoch": 1.52,
+      "eval_google_bleu": 0.42486486486486486,
+      "eval_loss": 0.23396648466587067,
+      "eval_runtime": 331.3322,
+      "eval_samples_per_second": 5.644,
+      "eval_steps_per_second": 0.353,
+      "step": 400
+    }
+  ],
+  "max_steps": 1315,
+  "num_train_epochs": 5,
+  "total_flos": 8901903215468544.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16fc4243d6f430ec8fe2b89274d1ff01615f3711e78ebc5204631f4fb71ecdd6
+size 3247