initial commit

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "kravchenko/uk-mt5-base",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "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": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "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:bfbb0118ca7ba0184e111bf541ee4894abf663583d855a5874f429d503e0b0f6
+size 2352161

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10161e5fb5de13eaac1f9fe5ee5f00eca5f9ec55cad8ab148d3a58a999d90d58
+size 977332173

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a7b3013d2b269ba399fc616ee97837b63dfcbf3ab0fabf6f9720eabef9e720a
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83bc7ca6b4a76d8a5057cc8c3a7382eb81973db4af981691849d3d3186a573f2
+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/af67de6ceccc9b1f12679f3c9b1bcd0acc27e990b967b91fed2e8c326187dbdd.294ebaa4cd17bb284635004c92d2c4d522ec488c828dcce0c2471b6f28e3fe82", "name_or_path": "kravchenko/uk-mt5-base", "tokenizer_class": "T5Tokenizer"}

trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.25548699498176575,
+  "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": 0.0009239543726235742,
+      "loss": 0.8634,
+      "step": 200
+    },
+    {
+      "epoch": 0.76,
+      "eval_google_bleu": 0.42247763419483103,
+      "eval_loss": 0.30603110790252686,
+      "eval_runtime": 109.6559,
+      "eval_samples_per_second": 17.053,
+      "eval_steps_per_second": 0.538,
+      "step": 200
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.0008479087452471484,
+      "loss": 0.2909,
+      "step": 400
+    },
+    {
+      "epoch": 1.52,
+      "eval_google_bleu": 0.4226960400591444,
+      "eval_loss": 0.25548699498176575,
+      "eval_runtime": 109.6393,
+      "eval_samples_per_second": 17.056,
+      "eval_steps_per_second": 0.538,
+      "step": 400
+    }
+  ],
+  "max_steps": 2630,
+  "num_train_epochs": 10,
+  "total_flos": 3106659908413440.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:746c97bafc69da2b2698f396394f095a9105a530638bde3ce5ecd10af8ac6e76
+size 3247