upload model

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "VietAI/vit5-base",
+  "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": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "use_cache": true,
+  "vocab_size": 36096
+}

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": "4.45.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0072d5dc7a81f4bfcf19b73a6c214db1b6fe24fc30524008f3de47126ce74047
+size 903834408

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45f14d9e5a670a18e813af4eccca8da86126c37bf177b6f610e92da7e6c6fc2e
+size 1807760570

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bc9bd724dba780ab41d603fed85fcce7c1df2f59e52b978ed73183817633767
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1e7ae8bfe6d5d5becb2c8ccd9b0b88cf41ba8499dda77e4ee5af5a22d8f08fe
+size 1064

trainer_state.json

@@ -0,0 +1,87 @@
+{
+  "best_metric": 0.9207741618156433,
+  "best_model_checkpoint": "./vit5_summary/checkpoint-3939",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3939,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 226449.640625,
+      "learning_rate": 1.4815232722143866e-05,
+      "loss": 1.8534,
+      "step": 1313
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9617251753807068,
+      "eval_runtime": 117.5744,
+      "eval_samples_per_second": 25.516,
+      "eval_steps_per_second": 1.599,
+      "step": 1313
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 193718.5625,
+      "learning_rate": 7.407616361071933e-06,
+      "loss": 0.9963,
+      "step": 2626
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.9302210211753845,
+      "eval_runtime": 117.1769,
+      "eval_samples_per_second": 25.602,
+      "eval_steps_per_second": 1.604,
+      "step": 2626
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 169458.0625,
+      "learning_rate": 0.0,
+      "loss": 0.9445,
+      "step": 3939
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.9207741618156433,
+      "eval_runtime": 117.8605,
+      "eval_samples_per_second": 25.454,
+      "eval_steps_per_second": 1.595,
+      "step": 3939
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3939,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 1
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.836434710528e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90548ac777241dcad402c3d0c99144981fda42907eb54a5bcbaf8b50d193fa49
+size 5176