Hugging Face's logo

ssardorf
/
pegasus-summ

Text2Text Generation
Transformers
PyTorch
pegasus
Inference Endpoints
Model card Files Community
ssardorf commited on
Commit
56e0c06
•
1 Parent(s): a917647

Remove old checkpoints

Browse files
Files changed (20) hide show
  1. checkpoint-3500/config.json +0 -58
  2. checkpoint-3500/optimizer.pt +0 -3
  3. checkpoint-3500/pytorch_model.bin +0 -3
  4. checkpoint-3500/rng_state.pth +0 -3
  5. checkpoint-3500/scheduler.pt +0 -3
  6. checkpoint-3500/special_tokens_map.json +0 -1
  7. checkpoint-3500/tokenizer.json +0 -0
  8. checkpoint-3500/tokenizer_config.json +0 -1
  9. checkpoint-3500/trainer_state.json +0 -58
  10. checkpoint-3500/training_args.bin +0 -3
  11. checkpoint-500/config.json +0 -58
  12. checkpoint-500/optimizer.pt +0 -3
  13. checkpoint-500/pytorch_model.bin +0 -3
  14. checkpoint-500/rng_state.pth +0 -3
  15. checkpoint-500/scheduler.pt +0 -3
  16. checkpoint-500/special_tokens_map.json +0 -1
  17. checkpoint-500/tokenizer.json +0 -0
  18. checkpoint-500/tokenizer_config.json +0 -1
  19. checkpoint-500/trainer_state.json +0 -22
  20. checkpoint-500/training_args.bin +0 -3
checkpoint-3500/config.json DELETED
@@ -1,58 +0,0 @@
1
- {
2
- "_name_or_path": "google/pegasus-xsum",
3
- "activation_dropout": 0.1,
4
- "activation_function": "relu",
5
- "add_bias_logits": false,
6
- "add_final_layer_norm": true,
7
- "architectures": [
8
- "PegasusForConditionalGeneration"
9
- ],
10
- "attention_dropout": 0.1,
11
- "bos_token_id": 0,
12
- "classif_dropout": 0.0,
13
- "classifier_dropout": 0.0,
14
- "d_model": 1024,
15
- "decoder_attention_heads": 16,
16
- "decoder_ffn_dim": 4096,
17
- "decoder_layerdrop": 0.0,
18
- "decoder_layers": 16,
19
- "decoder_start_token_id": 0,
20
- "do_blenderbot_90_layernorm": false,
21
- "dropout": 0.1,
22
- "encoder_attention_heads": 16,
23
- "encoder_ffn_dim": 4096,
24
- "encoder_layerdrop": 0.0,
25
- "encoder_layers": 16,
26
- "eos_token_id": 1,
27
- "extra_pos_embeddings": 0,
28
- "force_bos_token_to_be_generated": false,
29
- "forced_eos_token_id": 1,
30
- "gradient_checkpointing": false,
31
- "id2label": {
32
- "0": "LABEL_0",
33
- "1": "LABEL_1",
34
- "2": "LABEL_2"
35
- },
36
- "init_std": 0.02,
37
- "is_encoder_decoder": true,
38
- "label2id": {
39
- "LABEL_0": 0,
40
- "LABEL_1": 1,
41
- "LABEL_2": 2
42
- },
43
- "length_penalty": 0.6,
44
- "max_length": 64,
45
- "max_position_embeddings": 1024,
46
- "model_type": "pegasus",
47
- "normalize_before": true,
48
- "normalize_embedding": false,
49
- "num_beams": 8,
50
- "num_hidden_layers": 16,
51
- "pad_token_id": 0,
52
- "scale_embedding": true,
53
- "static_position_embeddings": true,
54
- "torch_dtype": "float32",
55
- "transformers_version": "4.17.0.dev0",
56
- "use_cache": true,
57
- "vocab_size": 96103
58
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-3500/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a46fe2caae181bcfe9faad65f50227fe350b2b4e357eb7123ab70f0908a00e30
3
- size 4549979939
 
 
 
 
checkpoint-3500/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a4b66b7d6fe51ff02efdb0ae3a0cfed642e96c0059c1f3eac1d108e4854c7ca
3
- size 2283818289
 
 
 
 
checkpoint-3500/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:226e56293a1d48d342b06418e1449ef4ac6b608f0dbf9f5bea21ca35693e5603
3
- size 13483
 
 
 
 
checkpoint-3500/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:29b37186bb750ff5ab4dc66e07d14e3755b091bc5124d0e48401732903799dab
3
- size 623
 
 
 
 
checkpoint-3500/special_tokens_map.json DELETED
@@ -1 +0,0 @@
1
- {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask_2>", "additional_special_tokens": ["<mask_1>", "<unk_2>", "<unk_3>", "<unk_4>", "<unk_5>", "<unk_6>", "<unk_7>", "<unk_8>", "<unk_9>", "<unk_10>", "<unk_11>", "<unk_12>", "<unk_13>", "<unk_14>", "<unk_15>", "<unk_16>", "<unk_17>", "<unk_18>", "<unk_19>", "<unk_20>", "<unk_21>", "<unk_22>", "<unk_23>", "<unk_24>", "<unk_25>", "<unk_26>", "<unk_27>", "<unk_28>", "<unk_29>", "<unk_30>", "<unk_31>", "<unk_32>", "<unk_33>", "<unk_34>", "<unk_35>", "<unk_36>", "<unk_37>", "<unk_38>", "<unk_39>", "<unk_40>", "<unk_41>", "<unk_42>", "<unk_43>", "<unk_44>", "<unk_45>", "<unk_46>", "<unk_47>", "<unk_48>", "<unk_49>", "<unk_50>", "<unk_51>", "<unk_52>", "<unk_53>", "<unk_54>", "<unk_55>", "<unk_56>", "<unk_57>", "<unk_58>", "<unk_59>", "<unk_60>", "<unk_61>", "<unk_62>", "<unk_63>", "<unk_64>", "<unk_65>", "<unk_66>", "<unk_67>", "<unk_68>", "<unk_69>", "<unk_70>", "<unk_71>", "<unk_72>", "<unk_73>", "<unk_74>", "<unk_75>", "<unk_76>", "<unk_77>", "<unk_78>", "<unk_79>", "<unk_80>", "<unk_81>", "<unk_82>", "<unk_83>", "<unk_84>", "<unk_85>", "<unk_86>", "<unk_87>", "<unk_88>", "<unk_89>", "<unk_90>", "<unk_91>", "<unk_92>", "<unk_93>", "<unk_94>", "<unk_95>", "<unk_96>", "<unk_97>", "<unk_98>", "<unk_99>", "<unk_100>", "<unk_101>", "<unk_102>"]}
 
 
checkpoint-3500/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-3500/tokenizer_config.json DELETED
@@ -1 +0,0 @@
1
- {"pad_token": "<pad>", "eos_token": "</s>", "unk_token": "<unk>", "mask_token": "<mask_2>", "mask_token_sent": "<mask_1>", "offset": 103, "additional_special_tokens": ["<mask_1>", "<unk_2>", "<unk_3>", "<unk_4>", "<unk_5>", "<unk_6>", "<unk_7>", "<unk_8>", "<unk_9>", "<unk_10>", "<unk_11>", "<unk_12>", "<unk_13>", "<unk_14>", "<unk_15>", "<unk_16>", "<unk_17>", "<unk_18>", "<unk_19>", "<unk_20>", "<unk_21>", "<unk_22>", "<unk_23>", "<unk_24>", "<unk_25>", "<unk_26>", "<unk_27>", "<unk_28>", "<unk_29>", "<unk_30>", "<unk_31>", "<unk_32>", "<unk_33>", "<unk_34>", "<unk_35>", "<unk_36>", "<unk_37>", "<unk_38>", "<unk_39>", "<unk_40>", "<unk_41>", "<unk_42>", "<unk_43>", "<unk_44>", "<unk_45>", "<unk_46>", "<unk_47>", "<unk_48>", "<unk_49>", "<unk_50>", "<unk_51>", "<unk_52>", "<unk_53>", "<unk_54>", "<unk_55>", "<unk_56>", "<unk_57>", "<unk_58>", "<unk_59>", "<unk_60>", "<unk_61>", "<unk_62>", "<unk_63>", "<unk_64>", "<unk_65>", "<unk_66>", "<unk_67>", "<unk_68>", "<unk_69>", "<unk_70>", "<unk_71>", "<unk_72>", "<unk_73>", "<unk_74>", "<unk_75>", "<unk_76>", "<unk_77>", "<unk_78>", "<unk_79>", "<unk_80>", "<unk_81>", "<unk_82>", "<unk_83>", "<unk_84>", "<unk_85>", "<unk_86>", "<unk_87>", "<unk_88>", "<unk_89>", "<unk_90>", "<unk_91>", "<unk_92>", "<unk_93>", "<unk_94>", "<unk_95>", "<unk_96>", "<unk_97>", "<unk_98>", "<unk_99>", "<unk_100>", "<unk_101>", "<unk_102>"], "model_max_length": 512, "special_tokens_map_file": null, "full_tokenizer_file": null, "name_or_path": "google/pegasus-xsum", "tokenizer_class": "PegasusTokenizer"}
 
 
checkpoint-3500/trainer_state.json DELETED
@@ -1,58 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 1.4,
5
- "global_step": 3500,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 0.2,
12
- "learning_rate": 4.666666666666667e-05,
13
- "loss": 1.7226,
14
- "step": 500
15
- },
16
- {
17
- "epoch": 0.4,
18
- "learning_rate": 4.3333333333333334e-05,
19
- "loss": 1.27,
20
- "step": 1000
21
- },
22
- {
23
- "epoch": 0.6,
24
- "learning_rate": 4e-05,
25
- "loss": 1.1669,
26
- "step": 1500
27
- },
28
- {
29
- "epoch": 0.8,
30
- "learning_rate": 3.6666666666666666e-05,
31
- "loss": 1.1489,
32
- "step": 2000
33
- },
34
- {
35
- "epoch": 1.0,
36
- "learning_rate": 3.3333333333333335e-05,
37
- "loss": 1.1451,
38
- "step": 2500
39
- },
40
- {
41
- "epoch": 1.2,
42
- "learning_rate": 3e-05,
43
- "loss": 0.9993,
44
- "step": 3000
45
- },
46
- {
47
- "epoch": 1.4,
48
- "learning_rate": 2.6666666666666667e-05,
49
- "loss": 1.0227,
50
- "step": 3500
51
- }
52
- ],
53
- "max_steps": 7500,
54
- "num_train_epochs": 3,
55
- "total_flos": 2.9293040335159296e+16,
56
- "trial_name": null,
57
- "trial_params": null
58
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-3500/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:790c0dd74ccf769eee75352a8807625e2b2074b043f85cf2ac0b75a9375b5fc8
3
- size 3119
 
 
 
 
checkpoint-500/config.json DELETED
@@ -1,58 +0,0 @@
1
- {
2
- "_name_or_path": "google/pegasus-xsum",
3
- "activation_dropout": 0.1,
4
- "activation_function": "relu",
5
- "add_bias_logits": false,
6
- "add_final_layer_norm": true,
7
- "architectures": [
8
- "PegasusForConditionalGeneration"
9
- ],
10
- "attention_dropout": 0.1,
11
- "bos_token_id": 0,
12
- "classif_dropout": 0.0,
13
- "classifier_dropout": 0.0,
14
- "d_model": 1024,
15
- "decoder_attention_heads": 16,
16
- "decoder_ffn_dim": 4096,
17
- "decoder_layerdrop": 0.0,
18
- "decoder_layers": 16,
19
- "decoder_start_token_id": 0,
20
- "do_blenderbot_90_layernorm": false,
21
- "dropout": 0.1,
22
- "encoder_attention_heads": 16,
23
- "encoder_ffn_dim": 4096,
24
- "encoder_layerdrop": 0.0,
25
- "encoder_layers": 16,
26
- "eos_token_id": 1,
27
- "extra_pos_embeddings": 0,
28
- "force_bos_token_to_be_generated": false,
29
- "forced_eos_token_id": 1,
30
- "gradient_checkpointing": false,
31
- "id2label": {
32
- "0": "LABEL_0",
33
- "1": "LABEL_1",
34
- "2": "LABEL_2"
35
- },
36
- "init_std": 0.02,
37
- "is_encoder_decoder": true,
38
- "label2id": {
39
- "LABEL_0": 0,
40
- "LABEL_1": 1,
41
- "LABEL_2": 2
42
- },
43
- "length_penalty": 0.6,
44
- "max_length": 64,
45
- "max_position_embeddings": 1024,
46
- "model_type": "pegasus",
47
- "normalize_before": true,
48
- "normalize_embedding": false,
49
- "num_beams": 8,
50
- "num_hidden_layers": 16,
51
- "pad_token_id": 0,
52
- "scale_embedding": true,
53
- "static_position_embeddings": true,
54
- "torch_dtype": "float32",
55
- "transformers_version": "4.17.0.dev0",
56
- "use_cache": true,
57
- "vocab_size": 96103
58
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-500/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6c76003d8d3638079abd34181ef2b354b8b0d9e142870fe69f7a2c41ac24fc6
3
- size 4549979939
 
 
 
 
checkpoint-500/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d5cda17ec38b4a3c99ebd617d69f3b3804b49b115ec2ee5e780da3e0ac43f74
3
- size 2283818289
 
 
 
 
checkpoint-500/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff471bffc94440dc1487cd3206034d1b95182badf9ee9b17699e1906a1dc97bf
3
- size 13547
 
 
 
 
checkpoint-500/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bc047e0bff1c48264e6437483117c31be8505841b45d5837ebfb8a57067f543
3
- size 623
 
 
 
 
checkpoint-500/special_tokens_map.json DELETED
@@ -1 +0,0 @@
1
- {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask_2>", "additional_special_tokens": ["<mask_1>", "<unk_2>", "<unk_3>", "<unk_4>", "<unk_5>", "<unk_6>", "<unk_7>", "<unk_8>", "<unk_9>", "<unk_10>", "<unk_11>", "<unk_12>", "<unk_13>", "<unk_14>", "<unk_15>", "<unk_16>", "<unk_17>", "<unk_18>", "<unk_19>", "<unk_20>", "<unk_21>", "<unk_22>", "<unk_23>", "<unk_24>", "<unk_25>", "<unk_26>", "<unk_27>", "<unk_28>", "<unk_29>", "<unk_30>", "<unk_31>", "<unk_32>", "<unk_33>", "<unk_34>", "<unk_35>", "<unk_36>", "<unk_37>", "<unk_38>", "<unk_39>", "<unk_40>", "<unk_41>", "<unk_42>", "<unk_43>", "<unk_44>", "<unk_45>", "<unk_46>", "<unk_47>", "<unk_48>", "<unk_49>", "<unk_50>", "<unk_51>", "<unk_52>", "<unk_53>", "<unk_54>", "<unk_55>", "<unk_56>", "<unk_57>", "<unk_58>", "<unk_59>", "<unk_60>", "<unk_61>", "<unk_62>", "<unk_63>", "<unk_64>", "<unk_65>", "<unk_66>", "<unk_67>", "<unk_68>", "<unk_69>", "<unk_70>", "<unk_71>", "<unk_72>", "<unk_73>", "<unk_74>", "<unk_75>", "<unk_76>", "<unk_77>", "<unk_78>", "<unk_79>", "<unk_80>", "<unk_81>", "<unk_82>", "<unk_83>", "<unk_84>", "<unk_85>", "<unk_86>", "<unk_87>", "<unk_88>", "<unk_89>", "<unk_90>", "<unk_91>", "<unk_92>", "<unk_93>", "<unk_94>", "<unk_95>", "<unk_96>", "<unk_97>", "<unk_98>", "<unk_99>", "<unk_100>", "<unk_101>", "<unk_102>"]}
 
 
checkpoint-500/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/tokenizer_config.json DELETED
@@ -1 +0,0 @@
1
- {"pad_token": "<pad>", "eos_token": "</s>", "unk_token": "<unk>", "mask_token": "<mask_2>", "mask_token_sent": "<mask_1>", "offset": 103, "additional_special_tokens": ["<mask_1>", "<unk_2>", "<unk_3>", "<unk_4>", "<unk_5>", "<unk_6>", "<unk_7>", "<unk_8>", "<unk_9>", "<unk_10>", "<unk_11>", "<unk_12>", "<unk_13>", "<unk_14>", "<unk_15>", "<unk_16>", "<unk_17>", "<unk_18>", "<unk_19>", "<unk_20>", "<unk_21>", "<unk_22>", "<unk_23>", "<unk_24>", "<unk_25>", "<unk_26>", "<unk_27>", "<unk_28>", "<unk_29>", "<unk_30>", "<unk_31>", "<unk_32>", "<unk_33>", "<unk_34>", "<unk_35>", "<unk_36>", "<unk_37>", "<unk_38>", "<unk_39>", "<unk_40>", "<unk_41>", "<unk_42>", "<unk_43>", "<unk_44>", "<unk_45>", "<unk_46>", "<unk_47>", "<unk_48>", "<unk_49>", "<unk_50>", "<unk_51>", "<unk_52>", "<unk_53>", "<unk_54>", "<unk_55>", "<unk_56>", "<unk_57>", "<unk_58>", "<unk_59>", "<unk_60>", "<unk_61>", "<unk_62>", "<unk_63>", "<unk_64>", "<unk_65>", "<unk_66>", "<unk_67>", "<unk_68>", "<unk_69>", "<unk_70>", "<unk_71>", "<unk_72>", "<unk_73>", "<unk_74>", "<unk_75>", "<unk_76>", "<unk_77>", "<unk_78>", "<unk_79>", "<unk_80>", "<unk_81>", "<unk_82>", "<unk_83>", "<unk_84>", "<unk_85>", "<unk_86>", "<unk_87>", "<unk_88>", "<unk_89>", "<unk_90>", "<unk_91>", "<unk_92>", "<unk_93>", "<unk_94>", "<unk_95>", "<unk_96>", "<unk_97>", "<unk_98>", "<unk_99>", "<unk_100>", "<unk_101>", "<unk_102>"], "model_max_length": 512, "special_tokens_map_file": null, "full_tokenizer_file": null, "name_or_path": "google/pegasus-xsum", "tokenizer_class": "PegasusTokenizer"}
 
 
checkpoint-500/trainer_state.json DELETED
@@ -1,22 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 0.2,
5
- "global_step": 500,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 0.2,
12
- "learning_rate": 4.666666666666667e-05,
13
- "loss": 1.7226,
14
- "step": 500
15
- }
16
- ],
17
- "max_steps": 7500,
18
- "num_train_epochs": 3,
19
- "total_flos": 4137735615086592.0,
20
- "trial_name": null,
21
- "trial_params": null
22
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-500/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:790c0dd74ccf769eee75352a8807625e2b2074b043f85cf2ac0b75a9375b5fc8
3
- size 3119