Add T5 Model (#10)

- Add T5 Model (549d04d36614a495cad08cf0beec63fe2e27f4c8)


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

T5/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/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/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:591721fc8356d62f00f4a9ba27283c6206bbb7525bd09f9723eb9543f3347218
+size 242041896

T5/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed3e107e59eb9cad55257916cf03bbdd97ae63545ab6476fcb4d246c7cdbc3c8
+size 484163514

T5/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c2f3313d838d31eb4140bcddf8bed36e65022b5426590710fe0628a00951a02
+size 14244

T5/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69812f1367cdb2da45be042e64b0795c952c62e17e23c9c3be6a3a3ea42ad9c7
+size 1064

T5/trainer_state.json

@@ -0,0 +1,96 @@
+{
+  "best_metric": 1.530792474746704,
+  "best_model_checkpoint": "./results_v1/checkpoint-295",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 295,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.5825037956237793,
+      "eval_runtime": 15.4954,
+      "eval_samples_per_second": 480.399,
+      "eval_steps_per_second": 3.808,
+      "step": 59
+    },
+    {
+      "epoch": 1.694915254237288,
+      "grad_norm": 21800.6015625,
+      "learning_rate": 0.0003305084745762712,
+      "loss": 1.4355,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.5649447441101074,
+      "eval_runtime": 16.533,
+      "eval_samples_per_second": 450.251,
+      "eval_steps_per_second": 3.569,
+      "step": 118
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.5507193803787231,
+      "eval_runtime": 16.0878,
+      "eval_samples_per_second": 462.71,
+      "eval_steps_per_second": 3.667,
+      "step": 177
+    },
+    {
+      "epoch": 3.389830508474576,
+      "grad_norm": 14290.56640625,
+      "learning_rate": 0.00016101694915254236,
+      "loss": 1.4142,
+      "step": 200
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.5406986474990845,
+      "eval_runtime": 16.3245,
+      "eval_samples_per_second": 456.001,
+      "eval_steps_per_second": 3.614,
+      "step": 236
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.530792474746704,
+      "eval_runtime": 16.839,
+      "eval_samples_per_second": 442.07,
+      "eval_steps_per_second": 3.504,
+      "step": 295
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 295,
+  "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": 1259440051322880.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

T5/training_args.bin

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

T5/vi_tokenizer_32128.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18c7d44bfd2206f5356e89c4400a6c2889579a7d0da304e879e5eb42b555ce2e
+size 751485