Upload 14 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,61 @@
 ---
+language:
+- yo
+- yor
 license: apache-2.0
+base_model: google/mt5-small
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: mt5_yo_yor
+  results: []
 ---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# mt5_yo_yor
+
+This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7137
+- Bleu: 33.7206
+- Gen Len: 53.0782
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.31.0
+- Pytorch 2.0.1+cu117
+- Datasets 2.11.0
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 3.0,
+    "eval_bleu": 33.7206,
+    "eval_gen_len": 53.0782,
+    "eval_loss": 0.7137071490287781,
+    "eval_runtime": 205.7162,
+    "eval_samples": 1100,
+    "eval_samples_per_second": 5.347,
+    "eval_steps_per_second": 0.335,
+    "predict_bleu": 33.4199,
+    "predict_gen_len": 56.9864,
+    "predict_loss": 0.7419636249542236,
+    "predict_runtime": 216.3884,
+    "predict_samples": 1100,
+    "predict_samples_per_second": 5.083,
+    "predict_steps_per_second": 0.319,
+    "train_loss": 2.284148406300617,
+    "train_runtime": 1232.512,
+    "train_samples": 17900,
+    "train_samples_per_second": 43.57,
+    "train_steps_per_second": 2.724
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "google/mt5-small",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "mt5",
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "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": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 250112
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_bleu": 33.7206,
+    "eval_gen_len": 53.0782,
+    "eval_loss": 0.7137071490287781,
+    "eval_runtime": 205.7162,
+    "eval_samples": 1100,
+    "eval_samples_per_second": 5.347,
+    "eval_steps_per_second": 0.335
+}

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": "4.31.0"
+}

predict_results.json

@@ -0,0 +1,9 @@
+{
+    "predict_bleu": 33.4199,
+    "predict_gen_len": 56.9864,
+    "predict_loss": 0.7419636249542236,
+    "predict_runtime": 216.3884,
+    "predict_samples": 1100,
+    "predict_samples_per_second": 5.083,
+    "predict_steps_per_second": 0.319
+}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d4f3fefdcb7b7e8532db3105feeda0899fbf096c91ea3b78261277ce1f5fe7
+size 16330467

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "additional_special_tokens": null,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 2.284148406300617,
+    "train_runtime": 1232.512,
+    "train_samples": 17900,
+    "train_samples_per_second": 43.57,
+    "train_steps_per_second": 2.724
+}

trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 3357,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.2552874590408106e-05,
+      "loss": 6.2133,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.5105749180816204e-05,
+      "loss": 2.2643,
+      "step": 1000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 2.7658623771224308e-05,
+      "loss": 1.7468,
+      "step": 1500
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 2.021149836163241e-05,
+      "loss": 1.506,
+      "step": 2000
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 1.2764372952040512e-05,
+      "loss": 1.3734,
+      "step": 2500
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.317247542448615e-06,
+      "loss": 1.3065,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "step": 3357,
+      "total_flos": 6313176299397120.0,
+      "train_loss": 2.284148406300617,
+      "train_runtime": 1232.512,
+      "train_samples_per_second": 43.57,
+      "train_steps_per_second": 2.724
+    }
+  ],
+  "max_steps": 3357,
+  "num_train_epochs": 3,
+  "total_flos": 6313176299397120.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbf078fef04359a2a1d739b685c4f9b35b84595f226ecababc1945cfc26f42c4
+size 4091