initial files

config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "/home/nlp-text/dynamic/mzhao/acg/conversation_swc/pretrained/t5_base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "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,
+  "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": "4.19.2",
+  "use_cache": true,
+  "vocab_size": 32100
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:642c813c71236fcc4329e6e657ad0f28f94d8f875fce71d79e49d4ab2f282fa3
+size 891614783

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 12702,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.803180601480082e-05,
+      "loss": 2.6193,
+      "step": 500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.6063612029601637e-05,
+      "loss": 2.4053,
+      "step": 1000
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.409541804440246e-05,
+      "loss": 2.3251,
+      "step": 1500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.212722405920328e-05,
+      "loss": 2.2622,
+      "step": 2000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.01590300740041e-05,
+      "loss": 2.2405,
+      "step": 2500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.819083608880492e-05,
+      "loss": 2.1981,
+      "step": 3000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.622264210360573e-05,
+      "loss": 2.1864,
+      "step": 3500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.425444811840655e-05,
+      "loss": 2.1688,
+      "step": 4000
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 3.228625413320737e-05,
+      "loss": 2.1147,
+      "step": 4500
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 3.0318060148008187e-05,
+      "loss": 2.089,
+      "step": 5000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 2.8349866162809007e-05,
+      "loss": 2.0734,
+      "step": 5500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 2.6381672177609828e-05,
+      "loss": 2.0585,
+      "step": 6000
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.4413478192410648e-05,
+      "loss": 2.0524,
+      "step": 6500
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 2.2445284207211465e-05,
+      "loss": 2.0465,
+      "step": 7000
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 2.0477090222012282e-05,
+      "loss": 2.0356,
+      "step": 7500
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.85088962368131e-05,
+      "loss": 2.0247,
+      "step": 8000
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 1.654070225161392e-05,
+      "loss": 2.0243,
+      "step": 8500
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 1.4572508266414739e-05,
+      "loss": 1.9859,
+      "step": 9000
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.2604314281215557e-05,
+      "loss": 1.9777,
+      "step": 9500
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 1.0636120296016376e-05,
+      "loss": 1.9901,
+      "step": 10000
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 8.667926310817193e-06,
+      "loss": 1.9684,
+      "step": 10500
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 6.699732325618014e-06,
+      "loss": 1.9806,
+      "step": 11000
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.731538340418832e-06,
+      "loss": 1.9642,
+      "step": 11500
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 2.7633443552196504e-06,
+      "loss": 1.9729,
+      "step": 12000
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 7.951503700204692e-07,
+      "loss": 1.9618,
+      "step": 12500
+    },
+    {
+      "epoch": 3.0,
+      "step": 12702,
+      "total_flos": 1.399103113734144e+16,
+      "train_loss": 2.1066248405263135,
+      "train_runtime": 10985.9481,
+      "train_samples_per_second": 36.991,
+      "train_steps_per_second": 1.156
+    }
+  ],
+  "max_steps": 12702,
+  "num_train_epochs": 3,
+  "total_flos": 1.399103113734144e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1902e423b98040bee2c41510872328dbcb37c8e2488f9ea1ed12bbacce4837c8
+size 3375