Hugging Face's logo

jsonfin17
/
financial_summary2

Text Generation
Transformers
PyTorch
TensorBoard
bart
Trained with AutoTrain
Inference Endpoints
Model card Files Metrics Community
1
jsonfin17 commited on
Commit
ec3335d
·
1 Parent(s): f23505c

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +9 -0
  2. adapter_config.json +21 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-150/README.md +34 -0
  5. checkpoint-150/adapter_config.json +21 -0
  6. checkpoint-150/adapter_model.bin +3 -0
  7. checkpoint-150/merges.txt +0 -0
  8. checkpoint-150/optimizer.pt +3 -0
  9. checkpoint-150/pytorch_model.bin +3 -0
  10. checkpoint-150/rng_state.pth +3 -0
  11. checkpoint-150/scheduler.pt +3 -0
  12. checkpoint-150/special_tokens_map.json +15 -0
  13. checkpoint-150/tokenizer.json +0 -0
  14. checkpoint-150/tokenizer_config.json +64 -0
  15. checkpoint-150/trainer_state.json +115 -0
  16. checkpoint-150/training_args.bin +3 -0
  17. checkpoint-150/vocab.json +0 -0
  18. config.json +71 -0
  19. generation_config.json +16 -0
  20. merges.txt +0 -0
  21. pytorch_model.bin +3 -0
  22. runs/Aug10_05-01-37_jason/events.out.tfevents.1691643698.jason.7592.0 +3 -0
  23. runs/Aug10_05-09-49_jason/events.out.tfevents.1691644190.jason.7941.0 +3 -0
  24. runs/Aug10_05-18-18_jason/events.out.tfevents.1691644698.jason.8324.0 +3 -0
  25. runs/Aug10_05-21-30_jason/events.out.tfevents.1691644890.jason.8673.0 +3 -0
  26. runs/Aug10_05-27-20_jason/events.out.tfevents.1691645240.jason.9090.0 +3 -0
  27. runs/Aug17_00-43-18_jason/events.out.tfevents.1692232998.jason.1696.0 +3 -0
  28. runs/Aug17_00-45-19_jason/events.out.tfevents.1692233120.jason.2032.0 +3 -0
  29. runs/Aug17_01-16-31_jason/events.out.tfevents.1692234992.jason.2490.0 +3 -0
  30. runs/Aug17_01-23-27_jason/events.out.tfevents.1692235408.jason.2851.0 +3 -0
  31. runs/Aug17_01-27-39_jason/events.out.tfevents.1692235659.jason.2955.0 +3 -0
  32. runs/Aug17_01-33-43_jason/events.out.tfevents.1692236023.jason.3327.0 +3 -0
  33. runs/Aug17_01-38-13_jason/events.out.tfevents.1692236293.jason.3993.0 +3 -0
  34. runs/Aug17_01-50-40_jason/events.out.tfevents.1692237040.jason.4722.0 +3 -0
  35. runs/Aug17_01-56-08_jason/events.out.tfevents.1692237368.jason.4865.0 +3 -0
  36. runs/Aug17_02-04-47_jason/events.out.tfevents.1692237887.jason.5330.0 +3 -0
  37. runs/Aug17_02-42-01_jason/events.out.tfevents.1692240121.jason.5859.0 +3 -0
  38. runs/Aug17_02-48-09_jason/events.out.tfevents.1692240489.jason.5998.0 +3 -0
  39. runs/Aug17_02-59-35_jason/events.out.tfevents.1692241175.jason.6149.0 +3 -0
  40. runs/Aug17_03-10-30_jason/events.out.tfevents.1692241831.jason.6289.0 +3 -0
  41. runs/Aug17_03-17-37_jason/events.out.tfevents.1692242257.jason.6420.0 +3 -0
  42. runs/Aug17_03-20-21_jason/events.out.tfevents.1692242422.jason.6523.0 +3 -0
  43. runs/Aug17_03-31-09_jason/events.out.tfevents.1692243069.jason.6695.0 +3 -0
  44. runs/Aug17_03-34-47_jason/events.out.tfevents.1692243288.jason.7001.0 +3 -0
  45. runs/Aug17_03-40-33_jason/events.out.tfevents.1692243634.jason.7118.0 +3 -0
  46. special_tokens_map.json +15 -0
  47. tokenizer.json +0 -0
  48. tokenizer_config.json +64 -0
  49. training_args.bin +3 -0
  50. training_params.json +41 -0
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - autotrain
4
+ - text-generation
5
+ widget:
6
+ - text: "I love AutoTrain because "
7
+ ---
8
+
9
+ # Model Trained Using AutoTrain
adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "philschmid/bart-large-cnn-samsum",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 32,
11
+ "lora_dropout": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 16,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3df52d1f0a22fd35e7f90c6a19dec05c29d96955b3aa62e704117e806d4b4cb0
3
+ size 6326545
checkpoint-150/README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float16
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: False
22
+ - load_in_4bit: True
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: nf4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float16
30
+ ### Framework versions
31
+
32
+ - PEFT 0.5.0.dev0
33
+
34
+ - PEFT 0.5.0.dev0
checkpoint-150/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "philschmid/bart-large-cnn-samsum",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 32,
11
+ "lora_dropout": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 16,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-150/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3df52d1f0a22fd35e7f90c6a19dec05c29d96955b3aa62e704117e806d4b4cb0
3
+ size 6326545
checkpoint-150/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-150/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61819019488f4418e8c9c051aa4027c8f57519e5736bd0dbeef9f0194c2c8148
3
+ size 6331781
checkpoint-150/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c152074a486243089e4fc0fdee0a373a30fb0e0a6e40eb5fd0d36fdafc97a155
3
+ size 443
checkpoint-150/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4573bfea6c6e8e013e3fa60bae1e3ea766dc00d2b31acb358d68da5f0d2f86f3
3
+ size 14575
checkpoint-150/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcd30f41673d8e64425b7224036f688453f28207459f1be2c176102e0006f138
3
+ size 627
checkpoint-150/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
checkpoint-150/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-150/tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "errors": "replace",
29
+ "mask_token": {
30
+ "__type": "AddedToken",
31
+ "content": "<mask>",
32
+ "lstrip": true,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "model_max_length": 1024,
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "tokenizer_class": "BartTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": {
57
+ "__type": "AddedToken",
58
+ "content": "<unk>",
59
+ "lstrip": false,
60
+ "normalized": true,
61
+ "rstrip": false,
62
+ "single_word": false
63
+ }
64
+ }
checkpoint-150/trainer_state.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 150,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.18,
13
+ "learning_rate": 0.00012,
14
+ "loss": 12.7445,
15
+ "step": 9
16
+ },
17
+ {
18
+ "epoch": 0.36,
19
+ "learning_rate": 0.00019555555555555556,
20
+ "loss": 11.2951,
21
+ "step": 18
22
+ },
23
+ {
24
+ "epoch": 0.54,
25
+ "learning_rate": 0.00018222222222222224,
26
+ "loss": 9.9077,
27
+ "step": 27
28
+ },
29
+ {
30
+ "epoch": 0.72,
31
+ "learning_rate": 0.00016888888888888889,
32
+ "loss": 8.6537,
33
+ "step": 36
34
+ },
35
+ {
36
+ "epoch": 0.9,
37
+ "learning_rate": 0.00015555555555555556,
38
+ "loss": 7.7628,
39
+ "step": 45
40
+ },
41
+ {
42
+ "epoch": 1.08,
43
+ "learning_rate": 0.00014222222222222224,
44
+ "loss": 7.0578,
45
+ "step": 54
46
+ },
47
+ {
48
+ "epoch": 1.26,
49
+ "learning_rate": 0.00012888888888888892,
50
+ "loss": 6.7923,
51
+ "step": 63
52
+ },
53
+ {
54
+ "epoch": 1.44,
55
+ "learning_rate": 0.00011555555555555555,
56
+ "loss": 6.4867,
57
+ "step": 72
58
+ },
59
+ {
60
+ "epoch": 1.62,
61
+ "learning_rate": 0.00010222222222222222,
62
+ "loss": 6.4616,
63
+ "step": 81
64
+ },
65
+ {
66
+ "epoch": 1.8,
67
+ "learning_rate": 8.888888888888889e-05,
68
+ "loss": 6.278,
69
+ "step": 90
70
+ },
71
+ {
72
+ "epoch": 1.98,
73
+ "learning_rate": 7.555555555555556e-05,
74
+ "loss": 6.2509,
75
+ "step": 99
76
+ },
77
+ {
78
+ "epoch": 2.16,
79
+ "learning_rate": 6.222222222222222e-05,
80
+ "loss": 6.1527,
81
+ "step": 108
82
+ },
83
+ {
84
+ "epoch": 2.34,
85
+ "learning_rate": 4.888888888888889e-05,
86
+ "loss": 6.1656,
87
+ "step": 117
88
+ },
89
+ {
90
+ "epoch": 2.52,
91
+ "learning_rate": 3.555555555555556e-05,
92
+ "loss": 6.0661,
93
+ "step": 126
94
+ },
95
+ {
96
+ "epoch": 2.7,
97
+ "learning_rate": 2.2222222222222223e-05,
98
+ "loss": 6.0176,
99
+ "step": 135
100
+ },
101
+ {
102
+ "epoch": 2.88,
103
+ "learning_rate": 8.88888888888889e-06,
104
+ "loss": 6.0408,
105
+ "step": 144
106
+ }
107
+ ],
108
+ "logging_steps": 9,
109
+ "max_steps": 150,
110
+ "num_train_epochs": 3,
111
+ "save_steps": 500,
112
+ "total_flos": 281424942858240.0,
113
+ "trial_name": null,
114
+ "trial_params": null
115
+ }
checkpoint-150/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:668bd080adfc74f0e44dcb63e750bfa238b9ce62e215ef6cfc97e2d36d613e00
3
+ size 4091
checkpoint-150/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "BartForCausalLM"
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_decoder": true,
38
+ "is_encoder_decoder": false,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1,
42
+ "LABEL_2": 2
43
+ },
44
+ "length_penalty": 2.0,
45
+ "max_length": 142,
46
+ "max_position_embeddings": 1024,
47
+ "min_length": 56,
48
+ "model_type": "bart",
49
+ "no_repeat_ngram_size": 3,
50
+ "normalize_before": false,
51
+ "num_beams": 4,
52
+ "num_hidden_layers": 12,
53
+ "output_past": true,
54
+ "pad_token_id": 1,
55
+ "prefix": " ",
56
+ "scale_embedding": false,
57
+ "task_specific_params": {
58
+ "summarization": {
59
+ "early_stopping": true,
60
+ "length_penalty": 2.0,
61
+ "max_length": 142,
62
+ "min_length": 56,
63
+ "no_repeat_ngram_size": 3,
64
+ "num_beams": 4
65
+ }
66
+ },
67
+ "torch_dtype": "float16",
68
+ "transformers_version": "4.32.0.dev0",
69
+ "use_cache": true,
70
+ "vocab_size": 50264
71
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "4.32.0.dev0"
16
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbeeae5ec425d4a75fdfb502aa5546b59a5e6e9ea5b41d73738b7404e8dc9508
3
+ size 508269501
runs/Aug10_05-01-37_jason/events.out.tfevents.1691643698.jason.7592.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:583a3d67261db8a1db1620a3269e5cad559729ed4dcb7208a0916cee6760bc45
3
+ size 5522
runs/Aug10_05-09-49_jason/events.out.tfevents.1691644190.jason.7941.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a458c2a69d6d1cff47dc1203409996382fd0ab38256d9675379cdc0efaf3f288
3
+ size 5522
runs/Aug10_05-18-18_jason/events.out.tfevents.1691644698.jason.8324.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a69ea56f77f86b608af2cb4a60da4ebb72fbf7c523892146f68a94b4c31c8ca0
3
+ size 5522
runs/Aug10_05-21-30_jason/events.out.tfevents.1691644890.jason.8673.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd6c9d6cd723a89e9e6a8ba45d7b8e7f8dc4b1b868b1195713d9a359237e24c7
3
+ size 5522
runs/Aug10_05-27-20_jason/events.out.tfevents.1691645240.jason.9090.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef7ed607acb2d8469b87f001678f379400e66f52853b4690d6c28c225aca7c9b
3
+ size 7092
runs/Aug17_00-43-18_jason/events.out.tfevents.1692232998.jason.1696.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6496eb09a062fe5b83db697dcfbde9cc1dd66ffb361a9c2566cd56fffc274d6
3
+ size 4184
runs/Aug17_00-45-19_jason/events.out.tfevents.1692233120.jason.2032.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1e9925c404566d747e7adb9f3a316a19bee074c6849cf55028db83841964d01
3
+ size 6186
runs/Aug17_01-16-31_jason/events.out.tfevents.1692234992.jason.2490.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44b409222cd104b71d4f2a88c6137fdde551bb8c36ddbb80cd7092b26692e814
3
+ size 8374
runs/Aug17_01-23-27_jason/events.out.tfevents.1692235408.jason.2851.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9213589c8ba0adaebb7deec35583fcd75e250e945fead6d7f9091536de64931
3
+ size 8380
runs/Aug17_01-27-39_jason/events.out.tfevents.1692235659.jason.2955.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:711b60dcd07c5f21897ebb0e4cfa1caa66f4aa12e5584d449bb0eac3a428caf3
3
+ size 8380
runs/Aug17_01-33-43_jason/events.out.tfevents.1692236023.jason.3327.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af7970f42ccd17042b9d0a24ff7bbd30b1fc7dde3900f89f67fbe468d0d6cd31
3
+ size 8380
runs/Aug17_01-38-13_jason/events.out.tfevents.1692236293.jason.3993.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:864c373bb93f7ae4eff4e5735af50ac64975a6af42fb8d54cd2cda8e9158a880
3
+ size 8380
runs/Aug17_01-50-40_jason/events.out.tfevents.1692237040.jason.4722.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49449eff22358ac2bc57b3ac7d457af455a3c853a72ffaa11c97bbcdbce503ed
3
+ size 8380
runs/Aug17_01-56-08_jason/events.out.tfevents.1692237368.jason.4865.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76c103fe18bfc951ef535295f3dc02190504bb651c4cdb91f2cf419d80cdb12f
3
+ size 8380
runs/Aug17_02-04-47_jason/events.out.tfevents.1692237887.jason.5330.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6d09750c4f84a81320b87fdd61add10694d17ec2ee6a0d2b85a08dd19ed5b62
3
+ size 8380
runs/Aug17_02-42-01_jason/events.out.tfevents.1692240121.jason.5859.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc823e2e1ea5a8a19ddfa3eec40209ce64fb2513274bdc1c822d19d41eab635a
3
+ size 8380
runs/Aug17_02-48-09_jason/events.out.tfevents.1692240489.jason.5998.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac4b0f037f2e3f5d41f5f2bd14cc38c4a6c454a3a1b5bcb480b31d79f7ab6ae1
3
+ size 8380
runs/Aug17_02-59-35_jason/events.out.tfevents.1692241175.jason.6149.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a162f1f2d0c15602bfaa5c1a0ff9ed33c0a917ecba3883465f8a754b4bdb15a9
3
+ size 8380
runs/Aug17_03-10-30_jason/events.out.tfevents.1692241831.jason.6289.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa281affc15d8e11839ef579c72a3e77c59fe760d9f28416373078ddf3cf9063
3
+ size 8380
runs/Aug17_03-17-37_jason/events.out.tfevents.1692242257.jason.6420.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c84e44451f6baf013fbc3d837d762fe9ab88c10a31ac85ad88de69f47a0b7bd
3
+ size 8380
runs/Aug17_03-20-21_jason/events.out.tfevents.1692242422.jason.6523.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9052253a9ca04448801fe5505bb1547faa82f0a8a471f5bf0d84e624666f4e49
3
+ size 8380
runs/Aug17_03-31-09_jason/events.out.tfevents.1692243069.jason.6695.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8591bbbe702b492025354d9d55bd9a42bf725aa7c07fa33b2f45c21d7b1cb87
3
+ size 4184
runs/Aug17_03-34-47_jason/events.out.tfevents.1692243288.jason.7001.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f2775912cd69cbcc6b8e16b2509bf31a4766028579a321de4c97c44ece5535a
3
+ size 8380
runs/Aug17_03-40-33_jason/events.out.tfevents.1692243634.jason.7118.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccc9bd6eb0398edc90cff16a29ce5dea5545202872ad52747df5a60d092136b6
3
+ size 8380
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "errors": "replace",
29
+ "mask_token": {
30
+ "__type": "AddedToken",
31
+ "content": "<mask>",
32
+ "lstrip": true,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "model_max_length": 1024,
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "tokenizer_class": "BartTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": {
57
+ "__type": "AddedToken",
58
+ "content": "<unk>",
59
+ "lstrip": false,
60
+ "normalized": true,
61
+ "rstrip": false,
62
+ "single_word": false
63
+ }
64
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:668bd080adfc74f0e44dcb63e750bfa238b9ce62e215ef6cfc97e2d36d613e00
3
+ size 4091
training_params.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name": "philschmid/bart-large-cnn-samsum",
3
+ "data_path": "banking77",
4
+ "train_split": "train",
5
+ "valid_split": null,
6
+ "text_column": "text",
7
+ "huggingface_token": null,
8
+ "learning_rate": 0.0002,
9
+ "num_train_epochs": 3,
10
+ "train_batch_size": 3,
11
+ "eval_batch_size": 4,
12
+ "warmup_ratio": 0.1,
13
+ "gradient_accumulation_steps": 1,
14
+ "optimizer": "adamw_torch",
15
+ "scheduler": "linear",
16
+ "weight_decay": 0.0,
17
+ "max_grad_norm": 1.0,
18
+ "seed": 42,
19
+ "add_eos_token": false,
20
+ "block_size": 2048,
21
+ "use_peft": true,
22
+ "lora_r": 16,
23
+ "lora_alpha": 32,
24
+ "lora_dropout": 0.05,
25
+ "training_type": "generic",
26
+ "train_on_inputs": false,
27
+ "logging_steps": -1,
28
+ "project_name": "financial-conversation-summarization",
29
+ "evaluation_strategy": "epoch",
30
+ "save_total_limit": 1,
31
+ "save_strategy": "epoch",
32
+ "auto_find_batch_size": false,
33
+ "fp16": false,
34
+ "push_to_hub": true,
35
+ "use_int8": false,
36
+ "model_max_length": 2048,
37
+ "repo_id": "jsonfin17/financial_summary2",
38
+ "use_int4": true,
39
+ "trainer": "sft",
40
+ "target_modules": null
41
+ }