gokulsrinivasagan commited on
Commit
a8696dc
1 Parent(s): 8e02d07

End of training

Browse files
README.md CHANGED
@@ -1,13 +1,28 @@
1
  ---
2
  library_name: transformers
 
 
3
  base_model: gokulsrinivasagan/distilbert_lda_5_v1
4
  tags:
5
  - generated_from_trainer
 
 
6
  metrics:
7
  - spearmanr
8
  model-index:
9
  - name: distilbert_lda_5_v1_stsb
10
- results: []
 
 
 
 
 
 
 
 
 
 
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,9 +30,9 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # distilbert_lda_5_v1_stsb
17
 
18
- This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_5_v1](https://huggingface.co/gokulsrinivasagan/distilbert_lda_5_v1) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 2.3650
21
  - Pearson: nan
22
  - Spearmanr: nan
23
  - Combined Score: nan
 
1
  ---
2
  library_name: transformers
3
+ language:
4
+ - en
5
  base_model: gokulsrinivasagan/distilbert_lda_5_v1
6
  tags:
7
  - generated_from_trainer
8
+ datasets:
9
+ - glue
10
  metrics:
11
  - spearmanr
12
  model-index:
13
  - name: distilbert_lda_5_v1_stsb
14
+ results:
15
+ - task:
16
+ name: Text Classification
17
+ type: text-classification
18
+ dataset:
19
+ name: GLUE STSB
20
+ type: glue
21
+ args: stsb
22
+ metrics:
23
+ - name: Spearmanr
24
+ type: spearmanr
25
+ value: .nan
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
30
 
31
  # distilbert_lda_5_v1_stsb
32
 
33
+ This model is a fine-tuned version of [gokulsrinivasagan/distilbert_lda_5_v1](https://huggingface.co/gokulsrinivasagan/distilbert_lda_5_v1) on the GLUE STSB dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 2.2568
36
  - Pearson: nan
37
  - Spearmanr: nan
38
  - Combined Score: nan
all_results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.0,
3
+ "eval_combined_score": NaN,
4
+ "eval_loss": 2.256788492202759,
5
+ "eval_pearson": NaN,
6
+ "eval_runtime": 0.645,
7
+ "eval_samples": 1500,
8
+ "eval_samples_per_second": 2325.648,
9
+ "eval_spearmanr": NaN,
10
+ "eval_steps_per_second": 9.303,
11
+ "total_flos": 2284624480859136.0,
12
+ "train_loss": 2.9096765656402144,
13
+ "train_runtime": 46.2023,
14
+ "train_samples": 5749,
15
+ "train_samples_per_second": 6221.552,
16
+ "train_steps_per_second": 24.891
17
+ }
eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.0,
3
+ "eval_combined_score": NaN,
4
+ "eval_loss": 2.256788492202759,
5
+ "eval_pearson": NaN,
6
+ "eval_runtime": 0.645,
7
+ "eval_samples": 1500,
8
+ "eval_samples_per_second": 2325.648,
9
+ "eval_spearmanr": NaN,
10
+ "eval_steps_per_second": 9.303
11
+ }
logs/events.out.tfevents.1732646463.ki-g0008.2135472.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db146c488c80ac837b8ffe9c1484165d52bde3b8b5820ad49456f18f2befd4c0
3
+ size 521
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 6.0,
3
+ "total_flos": 2284624480859136.0,
4
+ "train_loss": 2.9096765656402144,
5
+ "train_runtime": 46.2023,
6
+ "train_samples": 5749,
7
+ "train_samples_per_second": 6221.552,
8
+ "train_steps_per_second": 24.891
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 2.256788492202759,
3
+ "best_model_checkpoint": "distilbert_lda_5_v1_stsb/checkpoint-23",
4
+ "epoch": 6.0,
5
+ "eval_steps": 500,
6
+ "global_step": 138,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 6.748433589935303,
14
+ "learning_rate": 0.00098,
15
+ "loss": 6.3938,
16
+ "step": 23
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_combined_score": NaN,
21
+ "eval_loss": 2.256788492202759,
22
+ "eval_pearson": NaN,
23
+ "eval_runtime": 0.6384,
24
+ "eval_samples_per_second": 2349.63,
25
+ "eval_spearmanr": NaN,
26
+ "eval_steps_per_second": 9.399,
27
+ "step": 23
28
+ },
29
+ {
30
+ "epoch": 2.0,
31
+ "grad_norm": 18.032630920410156,
32
+ "learning_rate": 0.00096,
33
+ "loss": 2.2292,
34
+ "step": 46
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_combined_score": NaN,
39
+ "eval_loss": 2.2729742527008057,
40
+ "eval_pearson": NaN,
41
+ "eval_runtime": 0.636,
42
+ "eval_samples_per_second": 2358.504,
43
+ "eval_spearmanr": NaN,
44
+ "eval_steps_per_second": 9.434,
45
+ "step": 46
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "grad_norm": 3.141530990600586,
50
+ "learning_rate": 0.00094,
51
+ "loss": 2.2087,
52
+ "step": 69
53
+ },
54
+ {
55
+ "epoch": 3.0,
56
+ "eval_combined_score": -0.03073418981930874,
57
+ "eval_loss": 2.3179895877838135,
58
+ "eval_pearson": -0.030123554701908854,
59
+ "eval_runtime": 0.6514,
60
+ "eval_samples_per_second": 2302.65,
61
+ "eval_spearmanr": -0.03134482493670863,
62
+ "eval_steps_per_second": 9.211,
63
+ "step": 69
64
+ },
65
+ {
66
+ "epoch": 4.0,
67
+ "grad_norm": 3.1647350788116455,
68
+ "learning_rate": 0.00092,
69
+ "loss": 2.2043,
70
+ "step": 92
71
+ },
72
+ {
73
+ "epoch": 4.0,
74
+ "eval_combined_score": 0.009516354467436434,
75
+ "eval_loss": 2.654869794845581,
76
+ "eval_pearson": 0.007963371211781475,
77
+ "eval_runtime": 0.6535,
78
+ "eval_samples_per_second": 2295.416,
79
+ "eval_spearmanr": 0.011069337723091394,
80
+ "eval_steps_per_second": 9.182,
81
+ "step": 92
82
+ },
83
+ {
84
+ "epoch": 5.0,
85
+ "grad_norm": 14.778202056884766,
86
+ "learning_rate": 0.0009000000000000001,
87
+ "loss": 2.2273,
88
+ "step": 115
89
+ },
90
+ {
91
+ "epoch": 5.0,
92
+ "eval_combined_score": 0.0019123765153302998,
93
+ "eval_loss": 2.615886688232422,
94
+ "eval_pearson": 0.0017619346721126088,
95
+ "eval_runtime": 0.652,
96
+ "eval_samples_per_second": 2300.625,
97
+ "eval_spearmanr": 0.002062818358547991,
98
+ "eval_steps_per_second": 9.202,
99
+ "step": 115
100
+ },
101
+ {
102
+ "epoch": 6.0,
103
+ "grad_norm": 3.5717430114746094,
104
+ "learning_rate": 0.00088,
105
+ "loss": 2.1946,
106
+ "step": 138
107
+ },
108
+ {
109
+ "epoch": 6.0,
110
+ "eval_combined_score": NaN,
111
+ "eval_loss": 2.3650248050689697,
112
+ "eval_pearson": NaN,
113
+ "eval_runtime": 0.6498,
114
+ "eval_samples_per_second": 2308.569,
115
+ "eval_spearmanr": NaN,
116
+ "eval_steps_per_second": 9.234,
117
+ "step": 138
118
+ },
119
+ {
120
+ "epoch": 6.0,
121
+ "step": 138,
122
+ "total_flos": 2284624480859136.0,
123
+ "train_loss": 2.9096765656402144,
124
+ "train_runtime": 46.2023,
125
+ "train_samples_per_second": 6221.552,
126
+ "train_steps_per_second": 24.891
127
+ }
128
+ ],
129
+ "logging_steps": 1,
130
+ "max_steps": 1150,
131
+ "num_input_tokens_seen": 0,
132
+ "num_train_epochs": 50,
133
+ "save_steps": 500,
134
+ "stateful_callbacks": {
135
+ "EarlyStoppingCallback": {
136
+ "args": {
137
+ "early_stopping_patience": 5,
138
+ "early_stopping_threshold": 0.0
139
+ },
140
+ "attributes": {
141
+ "early_stopping_patience_counter": 5
142
+ }
143
+ },
144
+ "TrainerControl": {
145
+ "args": {
146
+ "should_epoch_stop": false,
147
+ "should_evaluate": false,
148
+ "should_log": false,
149
+ "should_save": true,
150
+ "should_training_stop": true
151
+ },
152
+ "attributes": {}
153
+ }
154
+ },
155
+ "total_flos": 2284624480859136.0,
156
+ "train_batch_size": 256,
157
+ "trial_name": null,
158
+ "trial_params": null
159
+ }