add models

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.99,
+    "train_loss": 0.7044082641601562,
+    "train_runtime": 1156.1087,
+    "train_samples": 7000,
+    "train_samples_per_second": 60.548,
+    "train_steps_per_second": 0.467
+}

combined_args.json

@@ -0,0 +1,159 @@
+{
+    "use_picard": false,
+    "launch_picard": false,
+    "picard_host": "localhost",
+    "picard_port": 9090,
+    "picard_mode": "parse_with_guards",
+    "picard_schedule": "incremental",
+    "picard_max_tokens_to_check": 2,
+    "model_name_or_path": "t5-small",
+    "config_name": null,
+    "tokenizer_name": null,
+    "cache_dir": "~/picard/transformers_cache",
+    "use_fast_tokenizer": true,
+    "model_revision": "main",
+    "use_auth_token": false,
+    "dataset": "spider",
+    "dataset_paths": {
+        "spider": "./seq2seq/datasets/spider",
+        "cosql": "./seq2seq/datasets/cosql",
+        "spider_realistic": "./seq2seq/datasets/spider_realistic",
+        "spider_syn": "./seq2seq/datasets/spider_syn",
+        "spider_dk": "./seq2seq/datasets/spider_dk"
+    },
+    "metric_config": "both",
+    "metric_paths": {
+        "spider": "./seq2seq/metrics/spider",
+        "spider_realistic": "./seq2seq/metrics/spider",
+        "cosql": "./seq2seq/metrics/cosql",
+        "spider_syn": "./seq2seq/metrics/spider",
+        "spider_dk": "./seq2seq/metrics/spider"
+    },
+    "test_suite_db_dir": null,
+    "data_config_file": null,
+    "test_sections": null,
+    "overwrite_cache": false,
+    "preprocessing_num_workers": null,
+    "max_source_length": 512,
+    "max_target_length": 512,
+    "val_max_target_length": 512,
+    "val_max_time": null,
+    "max_train_samples": null,
+    "max_val_samples": null,
+    "num_beams": 1,
+    "num_beam_groups": 1,
+    "diversity_penalty": null,
+    "num_return_sequences": null,
+    "ignore_pad_token_for_loss": true,
+    "source_prefix": "",
+    "schema_serialization_type": "peteshaw",
+    "schema_serialization_randomized": false,
+    "schema_serialization_with_db_id": true,
+    "schema_serialization_with_db_content": true,
+    "normalize_query": true,
+    "target_with_db_id": true,
+    "output_dir": "/home/jining/picard/train",
+    "overwrite_output_dir": true,
+    "do_train": true,
+    "do_eval": true,
+    "do_predict": false,
+    "evaluation_strategy": "steps",
+    "prediction_loss_only": false,
+    "per_device_train_batch_size": 8,
+    "per_device_eval_batch_size": 8,
+    "per_gpu_train_batch_size": "None",
+    "per_gpu_eval_batch_size": "None",
+    "gradient_accumulation_steps": 8,
+    "eval_accumulation_steps": "None",
+    "eval_delay": 0,
+    "learning_rate": 0.0001,
+    "weight_decay": 0.0,
+    "adam_beta1": 0.9,
+    "adam_beta2": 0.999,
+    "adam_epsilon": 1e-08,
+    "max_grad_norm": 1.0,
+    "num_train_epochs": 10,
+    "max_steps": -1,
+    "lr_scheduler_type": "constant",
+    "warmup_ratio": 0.0,
+    "warmup_steps": 0,
+    "log_level": -1,
+    "log_level_replica": -1,
+    "log_on_each_node": true,
+    "logging_dir": "/home/jining/picard/train/runs/Jul26_15-25-41_icu-gpu-4.sl.cloud9.ibm.com",
+    "logging_strategy": "steps",
+    "logging_first_step": false,
+    "logging_steps": 40000,
+    "logging_nan_inf_filter": true,
+    "save_strategy": "steps",
+    "save_steps": 64000,
+    "save_total_limit": 128,
+    "save_on_each_node": false,
+    "no_cuda": false,
+    "seed": 1,
+    "data_seed": "None",
+    "jit_mode_eval": false,
+    "use_ipex": false,
+    "bf16": false,
+    "fp16": false,
+    "fp16_opt_level": "O1",
+    "half_precision_backend": "auto",
+    "bf16_full_eval": false,
+    "fp16_full_eval": false,
+    "tf32": "None",
+    "xpu_backend": "None",
+    "tpu_num_cores": "None",
+    "tpu_metrics_debug": false,
+    "debug": "[]",
+    "dataloader_drop_last": false,
+    "eval_steps": 64000,
+    "dataloader_num_workers": 0,
+    "past_index": -1,
+    "run_name": "t5-spider",
+    "disable_tqdm": false,
+    "remove_unused_columns": true,
+    "label_names": "None",
+    "load_best_model_at_end": false,
+    "metric_for_best_model": "exact_match",
+    "greater_is_better": true,
+    "ignore_data_skip": false,
+    "sharded_ddp": "[]",
+    "fsdp": "[]",
+    "fsdp_min_num_params": 0,
+    "deepspeed": "None",
+    "label_smoothing_factor": 0.0,
+    "optim": "adafactor",
+    "adafactor": true,
+    "group_by_length": false,
+    "length_column_name": "length",
+    "report_to": "['tensorboard']",
+    "ddp_find_unused_parameters": "None",
+    "ddp_bucket_cap_mb": "None",
+    "dataloader_pin_memory": true,
+    "skip_memory_metrics": true,
+    "use_legacy_prediction_loop": false,
+    "push_to_hub": false,
+    "resume_from_checkpoint": "None",
+    "hub_model_id": "None",
+    "hub_strategy": "every_save",
+    "hub_token": "<HUB_TOKEN>",
+    "hub_private_repo": false,
+    "gradient_checkpointing": false,
+    "include_inputs_for_metrics": false,
+    "fp16_backend": "auto",
+    "push_to_hub_model_id": "None",
+    "push_to_hub_organization": "None",
+    "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
+    "_n_gpu": 2,
+    "mp_parameters": "",
+    "auto_find_batch_size": false,
+    "full_determinism": false,
+    "torchdynamo": "None",
+    "ray_scope": "last",
+    "sortish_sampler": false,
+    "predict_with_generate": true,
+    "generation_max_length": "None",
+    "generation_num_beams": "None",
+    "train_batch_size": 16,
+    "eval_batch_size": 16
+}

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "t5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "diversity_penalty": null,
+  "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,
+  "max_length": 512,
+  "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": "4.21.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32102
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c03c0de0e61859d0e96f8b186009786f696cb0b631992aac9ca0fea478879109
+size 242017019

runs/Jul26_15-25-41_icu-gpu-4.sl.cloud9.ibm.com/1658850513.2023797/events.out.tfevents.1658850513.icu-gpu-4.sl.cloud9.ibm.com.73577.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55eb73fa711215dd6adc69dec14820b50edad80b266a2dcaec837ac6343bd861
+size 5594

runs/Jul26_15-25-41_icu-gpu-4.sl.cloud9.ibm.com/events.out.tfevents.1658850513.icu-gpu-4.sl.cloud9.ibm.com.73577.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d783bdcee78167fafad4b3e0c4e7eb2f5f1fa4178d800da9f3850f2b5277aef
+size 4969

special_tokens_map.json

@@ -0,0 +1,107 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,112 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 512,
+  "name_or_path": "t5-small",
+  "pad_token": "<pad>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.99,
+    "train_loss": 0.7044082641601562,
+    "train_runtime": 1156.1087,
+    "train_samples": 7000,
+    "train_samples_per_second": 60.548,
+    "train_steps_per_second": 0.467
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.986301369863014,
+  "global_step": 540,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 9.99,
+      "step": 540,
+      "total_flos": 8562456167448576.0,
+      "train_loss": 0.7044082641601562,
+      "train_runtime": 1156.1087,
+      "train_samples_per_second": 60.548,
+      "train_steps_per_second": 0.467
+    }
+  ],
+  "max_steps": 540,
+  "num_train_epochs": 10,
+  "total_flos": 8562456167448576.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d448c3e680e65210ff4b47433a53e4edf5a5eef9fb1a631ba91481fb25e578a
+size 3439