gokulsrinivasagan
commited on
Commit
•
4ff04a1
1
Parent(s):
3200992
End of training
Browse files- README.md +19 -4
- all_results.json +15 -0
- eval_results.json +9 -0
- logs/events.out.tfevents.1732662292.ki-g0008.2137866.27 +3 -0
- train_results.json +9 -0
- trainer_state.json +211 -0
README.md
CHANGED
@@ -1,13 +1,28 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
|
|
|
|
3 |
base_model: gokulsrinivasagan/bert_tiny_lda_100_v1
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
metrics:
|
7 |
- accuracy
|
8 |
model-index:
|
9 |
- name: bert_tiny_lda_100_v1_rte
|
10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -15,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# bert_tiny_lda_100_v1_rte
|
17 |
|
18 |
-
This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1) on
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Accuracy: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
+
language:
|
4 |
+
- en
|
5 |
base_model: gokulsrinivasagan/bert_tiny_lda_100_v1
|
6 |
tags:
|
7 |
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- glue
|
10 |
metrics:
|
11 |
- accuracy
|
12 |
model-index:
|
13 |
- name: bert_tiny_lda_100_v1_rte
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Text Classification
|
17 |
+
type: text-classification
|
18 |
+
dataset:
|
19 |
+
name: GLUE RTE
|
20 |
+
type: glue
|
21 |
+
args: rte
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.5270758122743683
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
30 |
|
31 |
# bert_tiny_lda_100_v1_rte
|
32 |
|
33 |
+
This model is a fine-tuned version of [gokulsrinivasagan/bert_tiny_lda_100_v1](https://huggingface.co/gokulsrinivasagan/bert_tiny_lda_100_v1) on the GLUE RTE dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.6911
|
36 |
+
- Accuracy: 0.5271
|
37 |
|
38 |
## Model description
|
39 |
|
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.5270758122743683,
|
4 |
+
"eval_loss": 0.6910818815231323,
|
5 |
+
"eval_runtime": 0.0902,
|
6 |
+
"eval_samples": 277,
|
7 |
+
"eval_samples_per_second": 3069.608,
|
8 |
+
"eval_steps_per_second": 22.163,
|
9 |
+
"total_flos": 652967094988800.0,
|
10 |
+
"train_loss": 0.7079746341705322,
|
11 |
+
"train_runtime": 20.9087,
|
12 |
+
"train_samples": 2490,
|
13 |
+
"train_samples_per_second": 5954.454,
|
14 |
+
"train_steps_per_second": 23.913
|
15 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.5270758122743683,
|
4 |
+
"eval_loss": 0.6910818815231323,
|
5 |
+
"eval_runtime": 0.0902,
|
6 |
+
"eval_samples": 277,
|
7 |
+
"eval_samples_per_second": 3069.608,
|
8 |
+
"eval_steps_per_second": 22.163
|
9 |
+
}
|
logs/events.out.tfevents.1732662292.ki-g0008.2137866.27
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58b6f0630277f8c09a6bfe10593c4e165adc277b8d05dc8d3fc222a90a03a705
|
3 |
+
size 405
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"total_flos": 652967094988800.0,
|
4 |
+
"train_loss": 0.7079746341705322,
|
5 |
+
"train_runtime": 20.9087,
|
6 |
+
"train_samples": 2490,
|
7 |
+
"train_samples_per_second": 5954.454,
|
8 |
+
"train_steps_per_second": 23.913
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,211 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6910818815231323,
|
3 |
+
"best_model_checkpoint": "bert_tiny_lda_100_v1_rte/checkpoint-50",
|
4 |
+
"epoch": 10.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 100,
|
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": 0.8250333070755005,
|
14 |
+
"learning_rate": 0.00098,
|
15 |
+
"loss": 0.8226,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.5270758122743683,
|
21 |
+
"eval_loss": 0.7099644541740417,
|
22 |
+
"eval_runtime": 0.0907,
|
23 |
+
"eval_samples_per_second": 3054.549,
|
24 |
+
"eval_steps_per_second": 22.055,
|
25 |
+
"step": 10
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"grad_norm": 0.27419352531433105,
|
30 |
+
"learning_rate": 0.00096,
|
31 |
+
"loss": 0.7009,
|
32 |
+
"step": 20
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_accuracy": 0.4729241877256318,
|
37 |
+
"eval_loss": 0.7083004713058472,
|
38 |
+
"eval_runtime": 0.0923,
|
39 |
+
"eval_samples_per_second": 3001.194,
|
40 |
+
"eval_steps_per_second": 21.669,
|
41 |
+
"step": 20
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.0,
|
45 |
+
"grad_norm": 0.2973408102989197,
|
46 |
+
"learning_rate": 0.00094,
|
47 |
+
"loss": 0.696,
|
48 |
+
"step": 30
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.0,
|
52 |
+
"eval_accuracy": 0.4729241877256318,
|
53 |
+
"eval_loss": 0.6955804228782654,
|
54 |
+
"eval_runtime": 0.0912,
|
55 |
+
"eval_samples_per_second": 3038.309,
|
56 |
+
"eval_steps_per_second": 21.937,
|
57 |
+
"step": 30
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 4.0,
|
61 |
+
"grad_norm": 0.25628429651260376,
|
62 |
+
"learning_rate": 0.00092,
|
63 |
+
"loss": 0.695,
|
64 |
+
"step": 40
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 4.0,
|
68 |
+
"eval_accuracy": 0.5270758122743683,
|
69 |
+
"eval_loss": 0.6930421590805054,
|
70 |
+
"eval_runtime": 0.0958,
|
71 |
+
"eval_samples_per_second": 2892.623,
|
72 |
+
"eval_steps_per_second": 20.885,
|
73 |
+
"step": 40
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 5.0,
|
77 |
+
"grad_norm": 0.6449291706085205,
|
78 |
+
"learning_rate": 0.0009000000000000001,
|
79 |
+
"loss": 0.6933,
|
80 |
+
"step": 50
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 5.0,
|
84 |
+
"eval_accuracy": 0.5270758122743683,
|
85 |
+
"eval_loss": 0.6910818815231323,
|
86 |
+
"eval_runtime": 0.0889,
|
87 |
+
"eval_samples_per_second": 3114.696,
|
88 |
+
"eval_steps_per_second": 22.489,
|
89 |
+
"step": 50
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 6.0,
|
93 |
+
"grad_norm": 0.27499687671661377,
|
94 |
+
"learning_rate": 0.00088,
|
95 |
+
"loss": 0.6964,
|
96 |
+
"step": 60
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 6.0,
|
100 |
+
"eval_accuracy": 0.4729241877256318,
|
101 |
+
"eval_loss": 0.698697030544281,
|
102 |
+
"eval_runtime": 0.0888,
|
103 |
+
"eval_samples_per_second": 3117.998,
|
104 |
+
"eval_steps_per_second": 22.513,
|
105 |
+
"step": 60
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 7.0,
|
109 |
+
"grad_norm": 0.1044619083404541,
|
110 |
+
"learning_rate": 0.00086,
|
111 |
+
"loss": 0.694,
|
112 |
+
"step": 70
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 7.0,
|
116 |
+
"eval_accuracy": 0.5270758122743683,
|
117 |
+
"eval_loss": 0.6921958923339844,
|
118 |
+
"eval_runtime": 0.0893,
|
119 |
+
"eval_samples_per_second": 3100.888,
|
120 |
+
"eval_steps_per_second": 22.389,
|
121 |
+
"step": 70
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 8.0,
|
125 |
+
"grad_norm": 0.16408830881118774,
|
126 |
+
"learning_rate": 0.00084,
|
127 |
+
"loss": 0.6941,
|
128 |
+
"step": 80
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 8.0,
|
132 |
+
"eval_accuracy": 0.4729241877256318,
|
133 |
+
"eval_loss": 0.6951573491096497,
|
134 |
+
"eval_runtime": 0.0897,
|
135 |
+
"eval_samples_per_second": 3088.335,
|
136 |
+
"eval_steps_per_second": 22.298,
|
137 |
+
"step": 80
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 9.0,
|
141 |
+
"grad_norm": 0.14835208654403687,
|
142 |
+
"learning_rate": 0.00082,
|
143 |
+
"loss": 0.6942,
|
144 |
+
"step": 90
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 9.0,
|
148 |
+
"eval_accuracy": 0.5270758122743683,
|
149 |
+
"eval_loss": 0.6926190257072449,
|
150 |
+
"eval_runtime": 0.092,
|
151 |
+
"eval_samples_per_second": 3011.868,
|
152 |
+
"eval_steps_per_second": 21.746,
|
153 |
+
"step": 90
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 10.0,
|
157 |
+
"grad_norm": 0.11492882668972015,
|
158 |
+
"learning_rate": 0.0008,
|
159 |
+
"loss": 0.6932,
|
160 |
+
"step": 100
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 10.0,
|
164 |
+
"eval_accuracy": 0.4729241877256318,
|
165 |
+
"eval_loss": 0.6936765909194946,
|
166 |
+
"eval_runtime": 0.0892,
|
167 |
+
"eval_samples_per_second": 3106.792,
|
168 |
+
"eval_steps_per_second": 22.432,
|
169 |
+
"step": 100
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 10.0,
|
173 |
+
"step": 100,
|
174 |
+
"total_flos": 652967094988800.0,
|
175 |
+
"train_loss": 0.7079746341705322,
|
176 |
+
"train_runtime": 20.9087,
|
177 |
+
"train_samples_per_second": 5954.454,
|
178 |
+
"train_steps_per_second": 23.913
|
179 |
+
}
|
180 |
+
],
|
181 |
+
"logging_steps": 1,
|
182 |
+
"max_steps": 500,
|
183 |
+
"num_input_tokens_seen": 0,
|
184 |
+
"num_train_epochs": 50,
|
185 |
+
"save_steps": 500,
|
186 |
+
"stateful_callbacks": {
|
187 |
+
"EarlyStoppingCallback": {
|
188 |
+
"args": {
|
189 |
+
"early_stopping_patience": 5,
|
190 |
+
"early_stopping_threshold": 0.0
|
191 |
+
},
|
192 |
+
"attributes": {
|
193 |
+
"early_stopping_patience_counter": 5
|
194 |
+
}
|
195 |
+
},
|
196 |
+
"TrainerControl": {
|
197 |
+
"args": {
|
198 |
+
"should_epoch_stop": false,
|
199 |
+
"should_evaluate": false,
|
200 |
+
"should_log": false,
|
201 |
+
"should_save": true,
|
202 |
+
"should_training_stop": true
|
203 |
+
},
|
204 |
+
"attributes": {}
|
205 |
+
}
|
206 |
+
},
|
207 |
+
"total_flos": 652967094988800.0,
|
208 |
+
"train_batch_size": 256,
|
209 |
+
"trial_name": null,
|
210 |
+
"trial_params": null
|
211 |
+
}
|