ajaydahiya8822 commited on
Commit
db47bd0
1 Parent(s): 158ed67

Upload 12 files

Browse files
all_results.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_gen_len": 59.9829,
4
+ "eval_loss": 1.3891159296035767,
5
+ "eval_mem_cpu_alloc_delta": 78528783,
6
+ "eval_mem_cpu_peaked_delta": 2605953,
7
+ "eval_mem_gpu_alloc_delta": 0,
8
+ "eval_mem_gpu_peaked_delta": 980464128,
9
+ "eval_rouge1": 42.621,
10
+ "eval_rouge2": 21.9825,
11
+ "eval_rougeL": 33.034,
12
+ "eval_rougeLsum": 39.6783,
13
+ "eval_runtime": 29.301,
14
+ "eval_samples": 818,
15
+ "eval_samples_per_second": 27.917,
16
+ "init_mem_cpu_alloc_delta": 180674,
17
+ "init_mem_cpu_peaked_delta": 18282,
18
+ "init_mem_gpu_alloc_delta": 1625362944,
19
+ "init_mem_gpu_peaked_delta": 0,
20
+ "test_gen_len": 60.0757,
21
+ "test_loss": 1.4224162101745605,
22
+ "test_mem_cpu_alloc_delta": 82666029,
23
+ "test_mem_cpu_peaked_delta": 2572070,
24
+ "test_mem_gpu_alloc_delta": 0,
25
+ "test_mem_gpu_peaked_delta": 1441433088,
26
+ "test_rouge1": 41.3174,
27
+ "test_rouge2": 20.8716,
28
+ "test_rougeL": 32.1337,
29
+ "test_rougeLsum": 38.4149,
30
+ "test_runtime": 34.32,
31
+ "test_samples": 819,
32
+ "test_samples_per_second": 23.864,
33
+ "train_mem_cpu_alloc_delta": 7544164,
34
+ "train_mem_cpu_peaked_delta": 413671172,
35
+ "train_mem_gpu_alloc_delta": 6524230144,
36
+ "train_mem_gpu_peaked_delta": 12734977024,
37
+ "train_runtime": 363.7124,
38
+ "train_samples": 14732,
39
+ "train_samples_per_second": 1.905
40
+ }
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-large-cnn",
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
+ "transformers_version": "4.4.2",
67
+ "use_cache": true,
68
+ "vocab_size": 50264
69
+ }
eval_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_gen_len": 59.9829,
4
+ "eval_loss": 1.3891159296035767,
5
+ "eval_mem_cpu_alloc_delta": 78528783,
6
+ "eval_mem_cpu_peaked_delta": 2605953,
7
+ "eval_mem_gpu_alloc_delta": 0,
8
+ "eval_mem_gpu_peaked_delta": 980464128,
9
+ "eval_rouge1": 42.621,
10
+ "eval_rouge2": 21.9825,
11
+ "eval_rougeL": 33.034,
12
+ "eval_rougeLsum": 39.6783,
13
+ "eval_runtime": 29.301,
14
+ "eval_samples": 818,
15
+ "eval_samples_per_second": 27.917
16
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +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}}
test_generations.txt ADDED
The diff for this file is too large to render. See raw diff
 
test_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "test_gen_len": 60.0757,
3
+ "test_loss": 1.4224162101745605,
4
+ "test_mem_cpu_alloc_delta": 82666029,
5
+ "test_mem_cpu_peaked_delta": 2572070,
6
+ "test_mem_gpu_alloc_delta": 0,
7
+ "test_mem_gpu_peaked_delta": 1441433088,
8
+ "test_rouge1": 41.3174,
9
+ "test_rouge2": 20.8716,
10
+ "test_rougeL": 32.1337,
11
+ "test_rougeLsum": 38.4149,
12
+ "test_runtime": 34.32,
13
+ "test_samples": 819,
14
+ "test_samples_per_second": 23.864
15
+ }
tokenizer_config.json ADDED
@@ -0,0 +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>", "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-large-cnn"}
train_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "init_mem_cpu_alloc_delta": 180674,
4
+ "init_mem_cpu_peaked_delta": 18282,
5
+ "init_mem_gpu_alloc_delta": 1625362944,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 7544164,
8
+ "train_mem_cpu_peaked_delta": 413671172,
9
+ "train_mem_gpu_alloc_delta": 6524230144,
10
+ "train_mem_gpu_peaked_delta": 12734977024,
11
+ "train_runtime": 363.7124,
12
+ "train_samples": 14732,
13
+ "train_samples_per_second": 1.905
14
+ }
trainer_state.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 693,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.16,
12
+ "learning_rate": 1.3924963924963927e-05,
13
+ "loss": 1.2342,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 3.0,
18
+ "step": 693,
19
+ "total_flos": 3.5424926764630016e+16,
20
+ "train_runtime": 363.7124,
21
+ "train_samples_per_second": 1.905
22
+ }
23
+ ],
24
+ "max_steps": 693,
25
+ "num_train_epochs": 3,
26
+ "total_flos": 3.5424926764630016e+16,
27
+ "trial_name": null,
28
+ "trial_params": null
29
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:089267ebad1d0e44144bf11503446d8f02d6ac1efd1d78d1084e457061548a66
3
+ size 2351
vocab.json ADDED
The diff for this file is too large to render. See raw diff