Hugging Face's logo

alex2awesome
/
discourse-prediction__basic

Text Classification
Transformers
Safetensors
albert
Model card Files Community
Alex Spangher commited on
Commit
2054f8f
·
1 Parent(s): f02ef2b

e

Browse files
Files changed (8) hide show
  1. all_results.json +16 -0
  2. config.json +57 -0
  3. model.safetensors +3 -0
  4. post-training eval_results.json +10 -0
  5. prediction_output.jsonl +0 -0
  6. train_results.json +8 -0
  7. trainer_state.json +119 -0
  8. training_args.bin +3 -0
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_samples": 2820,
4
+ "test_accuracy": 0.5429078014184398,
5
+ "test_loss": 1.4821960926055908,
6
+ "test_macro_f1": 0.34723773230887656,
7
+ "test_micro_f1": 0.5429078014184398,
8
+ "test_runtime": 35.207,
9
+ "test_samples_per_second": 80.098,
10
+ "test_steps_per_second": 0.653,
11
+ "train_loss": 1.5852480240613014,
12
+ "train_runtime": 2084.5163,
13
+ "train_samples": 15278,
14
+ "train_samples_per_second": 21.988,
15
+ "train_steps_per_second": 0.688
16
+ }
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "albert-xxlarge-v2",
3
+ "architectures": [
4
+ "AlbertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout_prob": 0.1,
9
+ "down_scale_factor": 1,
10
+ "embedding_size": 128,
11
+ "eos_token_id": 3,
12
+ "gap_size": 0,
13
+ "hidden_act": "gelu_new",
14
+ "hidden_dropout_prob": 0,
15
+ "hidden_size": 4096,
16
+ "id2label": {
17
+ "0": "NA",
18
+ "1": "Main",
19
+ "2": "Cause_Specific",
20
+ "3": "Distant_Anecdotal",
21
+ "4": "Distant_Evaluation",
22
+ "5": "Main_Consequence",
23
+ "6": "Distant_Historical",
24
+ "7": "Cause_General",
25
+ "8": "Distant_Expectations_Consequences"
26
+ },
27
+ "initializer_range": 0.02,
28
+ "inner_group_num": 1,
29
+ "intermediate_size": 16384,
30
+ "label2id": {
31
+ "Cause_General": 7,
32
+ "Cause_Specific": 2,
33
+ "Distant_Anecdotal": 3,
34
+ "Distant_Evaluation": 4,
35
+ "Distant_Expectations_Consequences": 8,
36
+ "Distant_Historical": 6,
37
+ "Main": 1,
38
+ "Main_Consequence": 5,
39
+ "NA": 0
40
+ },
41
+ "layer_norm_eps": 1e-12,
42
+ "layers_to_keep": [],
43
+ "max_position_embeddings": 512,
44
+ "model_type": "albert",
45
+ "net_structure_type": 0,
46
+ "num_attention_heads": 64,
47
+ "num_hidden_groups": 1,
48
+ "num_hidden_layers": 12,
49
+ "num_memory_blocks": 0,
50
+ "pad_token_id": 0,
51
+ "position_embedding_type": "absolute",
52
+ "problem_type": "single_label_classification",
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.36.0.dev0",
55
+ "type_vocab_size": 2,
56
+ "vocab_size": 30000
57
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:605d5c7585301ee48a8090c4f4a67cfca237edc24091aa65c6d4393c98ecd61c
3
+ size 890533308
post-training eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval_samples": 2820,
3
+ "test_accuracy": 0.5429078014184398,
4
+ "test_loss": 1.4821960926055908,
5
+ "test_macro_f1": 0.34723773230887656,
6
+ "test_micro_f1": 0.5429078014184398,
7
+ "test_runtime": 35.207,
8
+ "test_samples_per_second": 80.098,
9
+ "test_steps_per_second": 0.653
10
+ }
prediction_output.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 1.5852480240613014,
4
+ "train_runtime": 2084.5163,
5
+ "train_samples": 15278,
6
+ "train_samples_per_second": 21.988,
7
+ "train_steps_per_second": 0.688
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 200,
6
+ "global_step": 1434,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.42,
13
+ "eval_accuracy": 0.32553191489361705,
14
+ "eval_loss": 1.8123600482940674,
15
+ "eval_macro_f1": 0.124166903518118,
16
+ "eval_micro_f1": 0.32553191489361705,
17
+ "eval_runtime": 33.706,
18
+ "eval_samples_per_second": 83.665,
19
+ "eval_steps_per_second": 0.682,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 0.84,
24
+ "eval_accuracy": 0.32163120567375886,
25
+ "eval_loss": 1.7639718055725098,
26
+ "eval_macro_f1": 0.14556223336608437,
27
+ "eval_micro_f1": 0.32163120567375886,
28
+ "eval_runtime": 33.5096,
29
+ "eval_samples_per_second": 84.155,
30
+ "eval_steps_per_second": 0.686,
31
+ "step": 400
32
+ },
33
+ {
34
+ "epoch": 1.05,
35
+ "learning_rate": 3.2566248256624825e-05,
36
+ "loss": 1.8551,
37
+ "step": 500
38
+ },
39
+ {
40
+ "epoch": 1.26,
41
+ "eval_accuracy": 0.3219858156028369,
42
+ "eval_loss": 1.7540267705917358,
43
+ "eval_macro_f1": 0.14782422014060434,
44
+ "eval_micro_f1": 0.3219858156028369,
45
+ "eval_runtime": 34.4226,
46
+ "eval_samples_per_second": 81.923,
47
+ "eval_steps_per_second": 0.668,
48
+ "step": 600
49
+ },
50
+ {
51
+ "epoch": 1.67,
52
+ "eval_accuracy": 0.46879432624113476,
53
+ "eval_loss": 1.695299744606018,
54
+ "eval_macro_f1": 0.21879212132843792,
55
+ "eval_micro_f1": 0.46879432624113476,
56
+ "eval_runtime": 35.6369,
57
+ "eval_samples_per_second": 79.131,
58
+ "eval_steps_per_second": 0.645,
59
+ "step": 800
60
+ },
61
+ {
62
+ "epoch": 2.09,
63
+ "learning_rate": 1.5132496513249652e-05,
64
+ "loss": 1.5754,
65
+ "step": 1000
66
+ },
67
+ {
68
+ "epoch": 2.09,
69
+ "eval_accuracy": 0.5046099290780142,
70
+ "eval_loss": 1.5334745645523071,
71
+ "eval_macro_f1": 0.29034421431874385,
72
+ "eval_micro_f1": 0.5046099290780142,
73
+ "eval_runtime": 34.2142,
74
+ "eval_samples_per_second": 82.422,
75
+ "eval_steps_per_second": 0.672,
76
+ "step": 1000
77
+ },
78
+ {
79
+ "epoch": 2.51,
80
+ "eval_accuracy": 0.5287234042553192,
81
+ "eval_loss": 1.5159926414489746,
82
+ "eval_macro_f1": 0.33578251623147193,
83
+ "eval_micro_f1": 0.5287234042553192,
84
+ "eval_runtime": 34.6936,
85
+ "eval_samples_per_second": 81.283,
86
+ "eval_steps_per_second": 0.663,
87
+ "step": 1200
88
+ },
89
+ {
90
+ "epoch": 2.93,
91
+ "eval_accuracy": 0.5382978723404256,
92
+ "eval_loss": 1.4883990287780762,
93
+ "eval_macro_f1": 0.34546874245733206,
94
+ "eval_micro_f1": 0.5382978723404256,
95
+ "eval_runtime": 35.0801,
96
+ "eval_samples_per_second": 80.387,
97
+ "eval_steps_per_second": 0.656,
98
+ "step": 1400
99
+ },
100
+ {
101
+ "epoch": 3.0,
102
+ "step": 1434,
103
+ "total_flos": 4067515429406100.0,
104
+ "train_loss": 1.5852480240613014,
105
+ "train_runtime": 2084.5163,
106
+ "train_samples_per_second": 21.988,
107
+ "train_steps_per_second": 0.688
108
+ }
109
+ ],
110
+ "logging_steps": 500,
111
+ "max_steps": 1434,
112
+ "num_input_tokens_seen": 0,
113
+ "num_train_epochs": 3,
114
+ "save_steps": 500,
115
+ "total_flos": 4067515429406100.0,
116
+ "train_batch_size": 32,
117
+ "trial_name": null,
118
+ "trial_params": null
119
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d2f138737942821e1f92014922c6845691eda9c73e96bfb92bfc9dfceed3e43
3
+ size 4664