Update new version of T5 (#14)

- Update new version of T5 (a216fe8b38188459e1a55db7cec1a9c8249f50c7)


Co-authored-by: Hoang Trung Khai <[email protected]>

T5_ver2/config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "t5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "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": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 32128
+}

T5_ver2/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": "4.46.3"
+}

T5_ver2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd644d98bd1050c70457b8529db0e18d35bde0e0877c64ce09229981fa0be16b
+size 242041896

T5_ver2/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3b5df5c7bc50ed8036075202178f6cc5e010ebf3782385a6ddf90ae6c39d786
+size 484163514

T5_ver2/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b31650900dea33c8f18e2b4dd4997626a0f5368b89ec466be164c249fc6451c
+size 14244

T5_ver2/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69b273d9b2ee662fb41f09ce2cad4738929d3cc2e4c449c5da4ac28babc1022d
+size 1064

T5_ver2/trainer_state.json

@@ -0,0 +1,117 @@
+{
+  "best_metric": 1.2436659336090088,
+  "best_model_checkpoint": "./results_v1/checkpoint-585",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 585,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8547008547008547,
+      "grad_norm": 16204.2978515625,
+      "learning_rate": 0.00041452991452991454,
+      "loss": 1.2355,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.3050023317337036,
+      "eval_runtime": 35.7149,
+      "eval_samples_per_second": 416.885,
+      "eval_steps_per_second": 3.276,
+      "step": 117
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "grad_norm": 21855.40625,
+      "learning_rate": 0.00032905982905982907,
+      "loss": 1.2163,
+      "step": 200
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.2828969955444336,
+      "eval_runtime": 34.9809,
+      "eval_samples_per_second": 425.632,
+      "eval_steps_per_second": 3.345,
+      "step": 234
+    },
+    {
+      "epoch": 2.564102564102564,
+      "grad_norm": 17783.169921875,
+      "learning_rate": 0.0002435897435897436,
+      "loss": 1.2163,
+      "step": 300
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.2669651508331299,
+      "eval_runtime": 34.8672,
+      "eval_samples_per_second": 427.02,
+      "eval_steps_per_second": 3.356,
+      "step": 351
+    },
+    {
+      "epoch": 3.4188034188034186,
+      "grad_norm": 15218.6376953125,
+      "learning_rate": 0.0001581196581196581,
+      "loss": 1.216,
+      "step": 400
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.251606822013855,
+      "eval_runtime": 34.7427,
+      "eval_samples_per_second": 428.551,
+      "eval_steps_per_second": 3.368,
+      "step": 468
+    },
+    {
+      "epoch": 4.273504273504273,
+      "grad_norm": 16033.8818359375,
+      "learning_rate": 7.264957264957266e-05,
+      "loss": 1.2226,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.2436659336090088,
+      "eval_runtime": 35.678,
+      "eval_samples_per_second": 417.316,
+      "eval_steps_per_second": 3.279,
+      "step": 585
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 585,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2518964691271680.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

T5_ver2/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98bd70546647df2bb00e52a0bb43ae210254e8e64f81eda19f84ab0660b86d67
+size 5240

T5_ver2/vi_tokenizer_32128.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bcb7e43d2a221e55098be0918ef7a89f6fb746c97610d2eea04bd7cb772e378
+size 749707