ShengdingHu commited on
Commit
a607c0a
·
1 Parent(s): 6616b3a

Training in progress, step 200

Browse files
config.json CHANGED
@@ -1,37 +1,57 @@
1
  {
2
- "_name_or_path": "../../../../plm_cache/roberta-base",
3
  "architectures": [
4
- "RobertaForSequenceClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "bos_token_id": 0,
8
- "classifier_dropout": null,
9
- "eos_token_id": 2,
10
- "finetuning_task": "mrpc",
11
- "hidden_act": "gelu",
12
- "hidden_dropout_prob": 0.1,
13
- "hidden_size": 768,
14
- "id2label": {
15
- "0": "not_equivalent",
16
- "1": "equivalent"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  },
18
- "initializer_range": 0.02,
19
- "intermediate_size": 3072,
20
- "label2id": {
21
- "equivalent": 1,
22
- "not_equivalent": 0
23
- },
24
- "layer_norm_eps": 1e-05,
25
- "max_position_embeddings": 514,
26
- "model_type": "roberta",
27
- "num_attention_heads": 12,
28
- "num_hidden_layers": 12,
29
- "pad_token_id": 1,
30
- "position_embedding_type": "absolute",
31
- "problem_type": "single_label_classification",
32
  "torch_dtype": "float32",
33
  "transformers_version": "4.16.0.dev0",
34
- "type_vocab_size": 1,
35
  "use_cache": true,
36
- "vocab_size": 50265
37
  }
 
1
  {
2
+ "_name_or_path": "../../../../plm_cache/t5-base",
3
  "architectures": [
4
+ "T5ForConditionalGeneration"
5
  ],
6
+ "d_ff": 3072,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "relu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "model_type": "t5",
17
+ "n_positions": 512,
18
+ "num_decoder_layers": 12,
19
+ "num_heads": 12,
20
+ "num_layers": 12,
21
+ "output_past": true,
22
+ "pad_token_id": 0,
23
+ "relative_attention_num_buckets": 32,
24
+ "task_specific_params": {
25
+ "summarization": {
26
+ "early_stopping": true,
27
+ "length_penalty": 2.0,
28
+ "max_length": 200,
29
+ "min_length": 30,
30
+ "no_repeat_ngram_size": 3,
31
+ "num_beams": 4,
32
+ "prefix": "summarize: "
33
+ },
34
+ "translation_en_to_de": {
35
+ "early_stopping": true,
36
+ "max_length": 300,
37
+ "num_beams": 4,
38
+ "prefix": "translate English to German: "
39
+ },
40
+ "translation_en_to_fr": {
41
+ "early_stopping": true,
42
+ "max_length": 300,
43
+ "num_beams": 4,
44
+ "prefix": "translate English to French: "
45
+ },
46
+ "translation_en_to_ro": {
47
+ "early_stopping": true,
48
+ "max_length": 300,
49
+ "num_beams": 4,
50
+ "prefix": "translate English to Romanian: "
51
+ }
52
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
  "torch_dtype": "float32",
54
  "transformers_version": "4.16.0.dev0",
 
55
  "use_cache": true,
56
+ "vocab_size": 32100
57
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d5d1f8d249ef7c917f0aabf9d0e8a1ab8a039183f1f1e1bcc3dfef845b8a696
3
- size 2689947
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e8152a898fba327e8e1da35f59aa7e5d0592d832ea0c848c5a79086dab9d436
3
+ size 1084131
runs/Feb11_18-41-14_node1/1644576262.779724/events.out.tfevents.1644576262.node1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6376ceb1a01853c673ac68681f835556d81bc6bce237b3d2a394f5806a2cedee
3
+ size 5011
runs/Feb11_18-41-14_node1/events.out.tfevents.1644576262.node1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:155c2b83f1b92be3576a1068c0dc11537b9500151a02851b91f1a2511748eaa9
3
+ size 4300
runs/Feb11_18-48-22_node1/1644577819.4992893/events.out.tfevents.1644577819.node1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eac025f96a951bc1c0b52fa072a2af6894fad5f7b339eff943aca7c72bad4b47
3
+ size 5011
runs/Feb11_18-48-22_node1/events.out.tfevents.1644577819.node1 ADDED
File without changes
runs/Feb11_19-10-34_node1/1644578055.334382/events.out.tfevents.1644578055.node1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e25fadc6058626e141bbe255ff66672b5b79ad6e19d3e3e2bf4e76dbe155f5c4
3
+ size 5011
runs/Feb11_19-10-34_node1/events.out.tfevents.1644578055.node1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:335548e74c2f176423fdd3b8a0dcf81c4e813c8188e9b86f00a86805813fae17
3
+ size 4300
runs/Feb11_19-21-50_node1/1644578706.6938386/events.out.tfevents.1644578706.node1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dee4aeb81d1f450f6f75384558fb1b588797cf057f68bbdebe71d261e658763
3
+ size 5011
runs/Feb11_19-21-50_node1/events.out.tfevents.1644578706.node1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39e90f1363ac97ca97585a869f3692ca3ba2b255def60b30fb83851959f40e10
3
+ size 4300
runs/Feb11_22-43-19_node1/1644590736.1581411/events.out.tfevents.1644590736.node1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2851248949e1c7024635b96f9e89a6921359e00ebae5a116331adcc5fa3d7a3
3
+ size 5011
runs/Feb11_22-43-19_node1/events.out.tfevents.1644590736.node1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b401d0b77a542600c6f84581b9e52e29ee611fdaa781569f166cb72fc3d642a
3
+ size 4300
runs/Feb11_22-49-28_node1/1644591134.5601833/events.out.tfevents.1644591134.node1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc01ffc94800aba735c358cfa922ec175ca15b5cbf34ed21fc93bb030e155840
3
+ size 5011
runs/Feb11_22-49-28_node1/events.out.tfevents.1644591134.node1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a93e34637f505e95ba2cdd28c6b990f0216f5e19ee37b0204bb54b76f2f5d4f
3
+ size 4300
runs/Feb11_22-55-12_node1/1644591513.7435496/events.out.tfevents.1644591513.node1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0211dc862ef4f776df6eee077a26d5fb7b3f37112b3c21133c13b0f256e01bae
3
+ size 5011
runs/Feb11_22-55-12_node1/events.out.tfevents.1644591513.node1 ADDED
File without changes
runs/Feb11_23-22-29_node1/1644593076.3588827/events.out.tfevents.1644593076.node1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d86b71a68d9e02a162fe9d64094f4d42690cddfb6ae622b7179a495a12c2d761
3
+ size 5011
runs/Feb11_23-22-29_node1/events.out.tfevents.1644593076.node1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be92d882ab2e2027ed0c46baeb89515f0a191bbaaa76186d1d8e8e4baec43207
3
+ size 4304
special_tokens_map.json CHANGED
@@ -1 +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}}
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "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>"]}
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1 +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"}
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "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>"], "special_tokens_map_file": null, "name_or_path": "../../../../plm_cache/t5-base", "tokenizer_class": "T5Tokenizer"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb5c19bac21de404530840d569a15ae28ae04d9c5fc783ec653c94030e66f065
3
- size 2991
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1012b30611760c9a969ee6d03278e1b6d653f11a88cb36b5abb2461bfca652d2
3
+ size 3183
training_config.json CHANGED
@@ -1 +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": "mrpc", "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": 20, "output_dir": "outputs/soft_prompt/t5-base/mrpc", "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": "mrpc", "test_dataset_config_name": ["en"], "test_dataset_name": "mrpc", "tokenizer_name": "../../../../plm_cache/t5-base", "unfrozen_modules": ["deltas"], "warmup_steps": 0}
 
1
+ {"dataset_config_name": ["en"], "delta_type": "bitfit", "do_eval": true, "do_test": true, "do_train": true, "eval_dataset_config_name": ["en"], "eval_dataset_name": "mrpc", "eval_steps": 200, "evaluation_strategy": "steps", "greater_is_better": true, "learning_rate": 0.0003, "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": 20, "output_dir": "outputs/bitfit/t5-base/mrpc", "overwrite_output_dir": true, "per_device_eval_batch_size": 100, "per_device_train_batch_size": 100, "predict_with_generate": true, "push_to_hub": true, "save_steps": 200, "save_strategy": "steps", "save_total_limit": 1, "seed": 42, "split_validation_test": true, "task_name": "mrpc", "test_dataset_config_name": ["en"], "test_dataset_name": "mrpc", "tokenizer_name": "../../../../plm_cache/t5-base", "warmup_steps": 500}