Training in progress, step 200

config.json

@@ -1,37 +1,35 @@
 {
-  "_name_or_path": "../../../../plm_cache/roberta-base",
+  "_name_or_path": "/home/hushengding/plm_cache/bigbird-roberta-large",
   "architectures": [
-    "RobertaForSequenceClassification"
+    "BigBirdForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
+  "attention_type": "block_sparse",
+  "block_size": 64,
+  "bos_token_id": 1,
   "classifier_dropout": null,
+  "dropout_rate": 0.0,
   "eos_token_id": 2,
-  "finetuning_task": "sst2",
-  "hidden_act": "gelu",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu_new",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "id2label": {
-    "0": "negative",
-    "1": "positive"
-  },
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "negative": 0,
-    "positive": 1
-  },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 4096,
+  "model_type": "big_bird",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_random_blocks": 3,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "problem_type": "single_label_classification",
+  "rescale_embeddings": false,
+  "sep_token_id": 66,
   "torch_dtype": "float32",
-  "transformers_version": "4.16.0.dev0",
-  "type_vocab_size": 1,
+  "transformers_version": "4.18.0",
+  "type_vocab_size": 2,
+  "use_bias": true,
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 50358
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97b85198a4f764a512668a9b6195426e63fa9d5f43bc824065bb21ee5c9213d5
-size 2670813
+oid sha256:6e8c0a9a0dfda06961c89632395fe183e80424b74556e68eca3cd31379827ead
+size 3177797

runs/Apr26_18-58-00_node1/1650971691.1516325/events.out.tfevents.1650971691.node1.3995991.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ad234157e3e21bcd53e6017bfe4b9e35a71c9be65b78e227123c378a37605ea
+size 5442

runs/Apr26_18-58-00_node1/events.out.tfevents.1650971691.node1.3995991.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05685bf7a2cc42782bdf3abd651f6f9679ed6ac3aaf2fe1b6dcab520bff0dc52
+size 4331

special_tokens_map.json

@@ -1 +1 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
+{"bos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

spiece.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
-size 791656
+oid sha256:fdc81e1fc9d42e0c08b86d5b280d05d7c5e9747c4231c648f2b56b8e1d893c82
+size 845731

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "special_tokens_map_file": null, "name_or_path": "../../../../plm_cache/roberta-base", "tokenizer_class": "RobertaTokenizer"}
+{"bos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": "/home/hushengding/plm_cache/bigbird-roberta-large/special_tokens_map.json", "name_or_path": "/home/hushengding/plm_cache/bigbird-roberta-large", "sp_model_kwargs": {}, "tokenizer_class": "BigBirdTokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b55d0648d1b0a06415f18ffb4570c4700baf8ccd5969e309dd37202ddb1a325d
-size 2991
+oid sha256:2a5bd23e6c586706fc70dfad4751c8d3173847382439d7afd74d51dfe92ae3c6
+size 3311

training_config.json

@@ -1 +1 @@
-{"dataset_config_name": ["en"], "delta_type": "soft_prompt", "do_eval": true, "do_test": true, "do_train": true, "eval_dataset_config_name": ["en"], "eval_dataset_name": "sst2", "eval_steps": 200, "evaluation_strategy": "steps", "greater_is_better": true, "learning_rate": 0.03, "load_best_model_at_end": true, "max_source_length": 128, "metric_for_best_model": "average_metrics", "model_name_or_path": "../../../../plm_cache/t5-base", "num_train_epochs": 3, "output_dir": "outputs/soft_prompt/t5-base/sst2", "overwrite_output_dir": true, "per_device_eval_batch_size": 32, "per_device_train_batch_size": 32, "predict_with_generate": true, "push_to_hub": true, "save_steps": 200, "save_strategy": "steps", "save_total_limit": 1, "seed": 42, "soft_token_num": 100, "split_validation_test": true, "task_name": "sst2", "test_dataset_config_name": ["en"], "test_dataset_name": "sst2", "token_init": false, "tokenizer_name": "../../../../plm_cache/t5-base", "unfrozen_modules": ["deltas"], "warmup_steps": 0}
+{"dataset_config_name": ["en"], "delta_type": "lora", "do_eval": true, "do_test": true, "do_train": true, "eval_dataset_config_name": ["en"], "eval_dataset_name": "sst2", "eval_steps": 200, "evaluation_strategy": "steps", "greater_is_better": true, "is_seq2seq": false, "learning_rate": 0.001, "load_best_model_at_end": true, "max_source_length": 128, "metric_for_best_model": "average_metrics", "model_name_or_path": "/home/hushengding/plm_cache/bigbird-roberta-large", "modified_modules": ["query", "key"], "num_train_epochs": 3, "output_dir": "outputs/lora/bigbird-roberta-large/sst2", "overwrite_output_dir": true, "per_device_eval_batch_size": 32, "per_device_train_batch_size": 32, "predict_with_generate": false, "push_to_hub": true, "save_steps": 200, "save_strategy": "steps", "save_total_limit": 1, "seed": 42, "split_validation_test": true, "task_name": "sst2", "test_dataset_config_name": ["en"], "test_dataset_name": "sst2", "tokenizer_name": "/home/hushengding/plm_cache/bigbird-roberta-large", "warmup_steps": 0}