Hugging Face's logo

vmarklynn
/
bart-large-cnn-samsum-icsi-ami

Text2Text Generation
Transformers
PyTorch
TensorBoard
bart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
3
Vincent Marklynn commited on
Commit
de0bb3e
•
1 Parent(s): c2a9b51

cleaned up dir

Browse files
Files changed (17) hide show
  1. .DS_Store +0 -0
  2. checkpoint-100/config.json +0 -70
  3. checkpoint-100/generation_config.json +0 -16
  4. checkpoint-100/optimizer.pt +0 -3
  5. checkpoint-100/pytorch_model.bin +0 -3
  6. checkpoint-100/rng_state.pth +0 -3
  7. checkpoint-100/scheduler.pt +0 -3
  8. checkpoint-100/trainer_state.json +0 -81
  9. checkpoint-100/training_args.bin +0 -3
  10. checkpoint-40/config.json +0 -70
  11. checkpoint-40/generation_config.json +0 -16
  12. checkpoint-40/optimizer.pt +0 -3
  13. checkpoint-40/pytorch_model.bin +0 -3
  14. checkpoint-40/rng_state.pth +0 -3
  15. checkpoint-40/scheduler.pt +0 -3
  16. checkpoint-40/trainer_state.json +0 -42
  17. checkpoint-40/training_args.bin +0 -3
.DS_Store CHANGED
Binary files a/.DS_Store and b/.DS_Store differ
 
checkpoint-100/config.json DELETED
@@ -1,70 +0,0 @@
1
- {
2
- "_name_or_path": "philschmid/bart-large-cnn-samsum",
3
- "_num_labels": 3,
4
- "activation_dropout": 0.0,
5
- "activation_function": "gelu",
6
- "add_final_layer_norm": false,
7
- "architectures": [
8
- "BartForConditionalGeneration"
9
- ],
10
- "attention_dropout": 0.0,
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": 12,
19
- "decoder_start_token_id": 2,
20
- "dropout": 0.1,
21
- "early_stopping": true,
22
- "encoder_attention_heads": 16,
23
- "encoder_ffn_dim": 4096,
24
- "encoder_layerdrop": 0.0,
25
- "encoder_layers": 12,
26
- "eos_token_id": 2,
27
- "force_bos_token_to_be_generated": true,
28
- "forced_bos_token_id": 0,
29
- "forced_eos_token_id": 2,
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": 2.0,
44
- "max_length": 142,
45
- "max_position_embeddings": 1024,
46
- "min_length": 56,
47
- "model_type": "bart",
48
- "no_repeat_ngram_size": 3,
49
- "normalize_before": false,
50
- "num_beams": 4,
51
- "num_hidden_layers": 12,
52
- "output_past": true,
53
- "pad_token_id": 1,
54
- "prefix": " ",
55
- "scale_embedding": false,
56
- "task_specific_params": {
57
- "summarization": {
58
- "early_stopping": true,
59
- "length_penalty": 2.0,
60
- "max_length": 142,
61
- "min_length": 56,
62
- "no_repeat_ngram_size": 3,
63
- "num_beams": 4
64
- }
65
- },
66
- "torch_dtype": "float32",
67
- "transformers_version": "4.26.0",
68
- "use_cache": true,
69
- "vocab_size": 50264
70
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-100/generation_config.json DELETED
@@ -1,16 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 0,
4
- "decoder_start_token_id": 2,
5
- "early_stopping": true,
6
- "eos_token_id": 2,
7
- "forced_bos_token_id": 0,
8
- "forced_eos_token_id": 2,
9
- "length_penalty": 2.0,
10
- "max_length": 142,
11
- "min_length": 56,
12
- "no_repeat_ngram_size": 3,
13
- "num_beams": 4,
14
- "pad_token_id": 1,
15
- "transformers_version": "4.26.0"
16
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-100/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbceb293d117c8f8f42f2fdd69f7ea55ec77450a1dd239d35f6e82b386daaf09
3
- size 3250609115
 
 
 
 
checkpoint-100/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca2db730013cead7febb250b2ba23f73b833ba04ab7007da6d0b26b9a1e4000f
3
- size 1625530125
 
 
 
 
checkpoint-100/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:168baffc75fe07640f4c86924b0139e77204f00fc48bc206978f4a43bc1372e2
3
- size 13617
 
 
 
 
checkpoint-100/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e5bce28bd2d99b5377778d2ca1ab4cdfcb65e303d135d27f19dd08b12dec6b0
3
- size 627
 
 
 
 
checkpoint-100/trainer_state.json DELETED
@@ -1,81 +0,0 @@
1
- {
2
- "best_metric": 3.1361048221588135,
3
- "best_model_checkpoint": "bart-large-cnn-samsum-acsi-ami/checkpoint-40",
4
- "epoch": 5.0,
5
- "global_step": 100,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 1.0,
12
- "eval_gen_len": 108.5,
13
- "eval_loss": 3.2094905376434326,
14
- "eval_rouge1": 39.8174,
15
- "eval_rouge2": 11.5559,
16
- "eval_rougeL": 24.0296,
17
- "eval_rougeLsum": 36.3048,
18
- "eval_runtime": 212.8556,
19
- "eval_samples_per_second": 0.188,
20
- "eval_steps_per_second": 0.023,
21
- "step": 20
22
- },
23
- {
24
- "epoch": 2.0,
25
- "eval_gen_len": 108.15,
26
- "eval_loss": 3.1361048221588135,
27
- "eval_rouge1": 39.7563,
28
- "eval_rouge2": 11.1286,
29
- "eval_rougeL": 23.2632,
30
- "eval_rougeLsum": 36.5664,
31
- "eval_runtime": 209.462,
32
- "eval_samples_per_second": 0.191,
33
- "eval_steps_per_second": 0.024,
34
- "step": 40
35
- },
36
- {
37
- "epoch": 3.0,
38
- "eval_gen_len": 122.95,
39
- "eval_loss": 3.1599366664886475,
40
- "eval_rouge1": 41.79,
41
- "eval_rouge2": 12.0967,
42
- "eval_rougeL": 23.5336,
43
- "eval_rougeLsum": 37.6859,
44
- "eval_runtime": 217.8522,
45
- "eval_samples_per_second": 0.184,
46
- "eval_steps_per_second": 0.023,
47
- "step": 60
48
- },
49
- {
50
- "epoch": 4.0,
51
- "eval_gen_len": 122.7,
52
- "eval_loss": 3.28777813911438,
53
- "eval_rouge1": 42.3161,
54
- "eval_rouge2": 12.2801,
55
- "eval_rougeL": 23.9352,
56
- "eval_rougeLsum": 38.2391,
57
- "eval_runtime": 212.5424,
58
- "eval_samples_per_second": 0.188,
59
- "eval_steps_per_second": 0.024,
60
- "step": 80
61
- },
62
- {
63
- "epoch": 5.0,
64
- "eval_gen_len": 129.225,
65
- "eval_loss": 3.3671374320983887,
66
- "eval_rouge1": 40.7968,
67
- "eval_rouge2": 10.7336,
68
- "eval_rougeL": 22.9434,
69
- "eval_rougeLsum": 36.4383,
70
- "eval_runtime": 216.6227,
71
- "eval_samples_per_second": 0.185,
72
- "eval_steps_per_second": 0.023,
73
- "step": 100
74
- }
75
- ],
76
- "max_steps": 100,
77
- "num_train_epochs": 5,
78
- "total_flos": 1690341589647360.0,
79
- "trial_name": null,
80
- "trial_params": null
81
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-100/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d16d4bbe3c1a3a528679fd7f699ed3222c17ad7a61017d9a075780b14236299a
3
- size 3643
 
 
 
 
checkpoint-40/config.json DELETED
@@ -1,70 +0,0 @@
1
- {
2
- "_name_or_path": "philschmid/bart-large-cnn-samsum",
3
- "_num_labels": 3,
4
- "activation_dropout": 0.0,
5
- "activation_function": "gelu",
6
- "add_final_layer_norm": false,
7
- "architectures": [
8
- "BartForConditionalGeneration"
9
- ],
10
- "attention_dropout": 0.0,
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": 12,
19
- "decoder_start_token_id": 2,
20
- "dropout": 0.1,
21
- "early_stopping": true,
22
- "encoder_attention_heads": 16,
23
- "encoder_ffn_dim": 4096,
24
- "encoder_layerdrop": 0.0,
25
- "encoder_layers": 12,
26
- "eos_token_id": 2,
27
- "force_bos_token_to_be_generated": true,
28
- "forced_bos_token_id": 0,
29
- "forced_eos_token_id": 2,
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": 2.0,
44
- "max_length": 142,
45
- "max_position_embeddings": 1024,
46
- "min_length": 56,
47
- "model_type": "bart",
48
- "no_repeat_ngram_size": 3,
49
- "normalize_before": false,
50
- "num_beams": 4,
51
- "num_hidden_layers": 12,
52
- "output_past": true,
53
- "pad_token_id": 1,
54
- "prefix": " ",
55
- "scale_embedding": false,
56
- "task_specific_params": {
57
- "summarization": {
58
- "early_stopping": true,
59
- "length_penalty": 2.0,
60
- "max_length": 142,
61
- "min_length": 56,
62
- "no_repeat_ngram_size": 3,
63
- "num_beams": 4
64
- }
65
- },
66
- "torch_dtype": "float32",
67
- "transformers_version": "4.26.0",
68
- "use_cache": true,
69
- "vocab_size": 50264
70
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-40/generation_config.json DELETED
@@ -1,16 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 0,
4
- "decoder_start_token_id": 2,
5
- "early_stopping": true,
6
- "eos_token_id": 2,
7
- "forced_bos_token_id": 0,
8
- "forced_eos_token_id": 2,
9
- "length_penalty": 2.0,
10
- "max_length": 142,
11
- "min_length": 56,
12
- "no_repeat_ngram_size": 3,
13
- "num_beams": 4,
14
- "pad_token_id": 1,
15
- "transformers_version": "4.26.0"
16
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-40/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ab8639119c1b8569dda18bf98ce0b7b3d8371bf3a909d27132ee761df310ee3
3
- size 3250609115
 
 
 
 
checkpoint-40/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:062a01b0385214a4b30120e4f5d9aea8075ca9dbb55344ab6b9d8e76ce9a85da
3
- size 1625530125
 
 
 
 
checkpoint-40/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2482b2cc11a386c3e0e0cc8802f1bb0a9c34f292d4e4acc11ae70f117bb1ae7
3
- size 13553
 
 
 
 
checkpoint-40/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:51cb491e0c1dd48d27b2af6be60fff4e0d3d16435dbf3bb4f48a394c2730266e
3
- size 627
 
 
 
 
checkpoint-40/trainer_state.json DELETED
@@ -1,42 +0,0 @@
1
- {
2
- "best_metric": 3.1361048221588135,
3
- "best_model_checkpoint": "bart-large-cnn-samsum-acsi-ami/checkpoint-40",
4
- "epoch": 2.0,
5
- "global_step": 40,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 1.0,
12
- "eval_gen_len": 108.5,
13
- "eval_loss": 3.2094905376434326,
14
- "eval_rouge1": 39.8174,
15
- "eval_rouge2": 11.5559,
16
- "eval_rougeL": 24.0296,
17
- "eval_rougeLsum": 36.3048,
18
- "eval_runtime": 212.8556,
19
- "eval_samples_per_second": 0.188,
20
- "eval_steps_per_second": 0.023,
21
- "step": 20
22
- },
23
- {
24
- "epoch": 2.0,
25
- "eval_gen_len": 108.15,
26
- "eval_loss": 3.1361048221588135,
27
- "eval_rouge1": 39.7563,
28
- "eval_rouge2": 11.1286,
29
- "eval_rougeL": 23.2632,
30
- "eval_rougeLsum": 36.5664,
31
- "eval_runtime": 209.462,
32
- "eval_samples_per_second": 0.191,
33
- "eval_steps_per_second": 0.024,
34
- "step": 40
35
- }
36
- ],
37
- "max_steps": 100,
38
- "num_train_epochs": 5,
39
- "total_flos": 676136635858944.0,
40
- "trial_name": null,
41
- "trial_params": null
42
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-40/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d16d4bbe3c1a3a528679fd7f699ed3222c17ad7a61017d9a075780b14236299a
3
- size 3643