End of training
Browse files- README.md +4 -2
- all_results.json +14 -0
- eval_results.json +9 -0
- logs/events.out.tfevents.1675047553.serv-3331.1557471.17 +3 -0
- train_results.json +8 -0
- trainer_state.json +115 -0
README.md
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
---
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_trainer
|
@@ -13,7 +15,7 @@ model-index:
|
|
13 |
name: Text Classification
|
14 |
type: text-classification
|
15 |
dataset:
|
16 |
-
name:
|
17 |
type: glue
|
18 |
config: sst2
|
19 |
split: validation
|
@@ -29,7 +31,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
29 |
|
30 |
# mobilebert_add_GLUE_Experiment_logit_kd_pretrain_sst2
|
31 |
|
32 |
-
This model is a fine-tuned version of [gokuls/mobilebert_add_pre-training-complete](https://huggingface.co/gokuls/mobilebert_add_pre-training-complete) on the
|
33 |
It achieves the following results on the evaluation set:
|
34 |
- Loss: nan
|
35 |
- Accuracy: 0.4908
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
license: apache-2.0
|
5 |
tags:
|
6 |
- generated_from_trainer
|
|
|
15 |
name: Text Classification
|
16 |
type: text-classification
|
17 |
dataset:
|
18 |
+
name: GLUE SST2
|
19 |
type: glue
|
20 |
config: sst2
|
21 |
split: validation
|
|
|
31 |
|
32 |
# mobilebert_add_GLUE_Experiment_logit_kd_pretrain_sst2
|
33 |
|
34 |
+
This model is a fine-tuned version of [gokuls/mobilebert_add_pre-training-complete](https://huggingface.co/gokuls/mobilebert_add_pre-training-complete) on the GLUE SST2 dataset.
|
35 |
It achieves the following results on the evaluation set:
|
36 |
- Loss: nan
|
37 |
- Accuracy: 0.4908
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 6.0,
|
3 |
+
"eval_accuracy": 0.4908256880733945,
|
4 |
+
"eval_loss": NaN,
|
5 |
+
"eval_runtime": 1.5282,
|
6 |
+
"eval_samples": 872,
|
7 |
+
"eval_samples_per_second": 570.604,
|
8 |
+
"eval_steps_per_second": 4.581,
|
9 |
+
"train_loss": 0.0,
|
10 |
+
"train_runtime": 1714.5809,
|
11 |
+
"train_samples": 67349,
|
12 |
+
"train_samples_per_second": 1964.008,
|
13 |
+
"train_steps_per_second": 15.368
|
14 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 6.0,
|
3 |
+
"eval_accuracy": 0.4908256880733945,
|
4 |
+
"eval_loss": NaN,
|
5 |
+
"eval_runtime": 1.5282,
|
6 |
+
"eval_samples": 872,
|
7 |
+
"eval_samples_per_second": 570.604,
|
8 |
+
"eval_steps_per_second": 4.581
|
9 |
+
}
|
logs/events.out.tfevents.1675047553.serv-3331.1557471.17
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4e4612ba6a94e286fb24688eb0ac4d6bff1f3fb6e3460dd4c525d2d7beb661c
|
3 |
+
size 363
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 6.0,
|
3 |
+
"train_loss": 0.0,
|
4 |
+
"train_runtime": 1714.5809,
|
5 |
+
"train_samples": 67349,
|
6 |
+
"train_samples_per_second": 1964.008,
|
7 |
+
"train_steps_per_second": 15.368
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": NaN,
|
3 |
+
"best_model_checkpoint": "mobilebert_add_GLUE_Experiment_logit_kd_pretrain_sst2/checkpoint-527",
|
4 |
+
"epoch": 6.0,
|
5 |
+
"global_step": 3162,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"learning_rate": 4.9e-05,
|
13 |
+
"loss": 0.0,
|
14 |
+
"step": 527
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.4908256880733945,
|
19 |
+
"eval_loss": NaN,
|
20 |
+
"eval_runtime": 1.5233,
|
21 |
+
"eval_samples_per_second": 572.445,
|
22 |
+
"eval_steps_per_second": 4.595,
|
23 |
+
"step": 527
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"learning_rate": 4.8e-05,
|
28 |
+
"loss": 0.0,
|
29 |
+
"step": 1054
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"eval_accuracy": 0.4908256880733945,
|
34 |
+
"eval_loss": NaN,
|
35 |
+
"eval_runtime": 1.5073,
|
36 |
+
"eval_samples_per_second": 578.515,
|
37 |
+
"eval_steps_per_second": 4.644,
|
38 |
+
"step": 1054
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 3.0,
|
42 |
+
"learning_rate": 4.7e-05,
|
43 |
+
"loss": 0.0,
|
44 |
+
"step": 1581
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"eval_accuracy": 0.4908256880733945,
|
49 |
+
"eval_loss": NaN,
|
50 |
+
"eval_runtime": 1.5082,
|
51 |
+
"eval_samples_per_second": 578.154,
|
52 |
+
"eval_steps_per_second": 4.641,
|
53 |
+
"step": 1581
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 4.0,
|
57 |
+
"learning_rate": 4.600000000000001e-05,
|
58 |
+
"loss": 0.0,
|
59 |
+
"step": 2108
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.0,
|
63 |
+
"eval_accuracy": 0.4908256880733945,
|
64 |
+
"eval_loss": NaN,
|
65 |
+
"eval_runtime": 1.5023,
|
66 |
+
"eval_samples_per_second": 580.451,
|
67 |
+
"eval_steps_per_second": 4.66,
|
68 |
+
"step": 2108
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 5.0,
|
72 |
+
"learning_rate": 4.5e-05,
|
73 |
+
"loss": 0.0,
|
74 |
+
"step": 2635
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 5.0,
|
78 |
+
"eval_accuracy": 0.4908256880733945,
|
79 |
+
"eval_loss": NaN,
|
80 |
+
"eval_runtime": 1.5058,
|
81 |
+
"eval_samples_per_second": 579.081,
|
82 |
+
"eval_steps_per_second": 4.649,
|
83 |
+
"step": 2635
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 6.0,
|
87 |
+
"learning_rate": 4.4000000000000006e-05,
|
88 |
+
"loss": 0.0,
|
89 |
+
"step": 3162
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 6.0,
|
93 |
+
"eval_accuracy": 0.4908256880733945,
|
94 |
+
"eval_loss": NaN,
|
95 |
+
"eval_runtime": 1.5043,
|
96 |
+
"eval_samples_per_second": 579.69,
|
97 |
+
"eval_steps_per_second": 4.653,
|
98 |
+
"step": 3162
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 6.0,
|
102 |
+
"step": 3162,
|
103 |
+
"total_flos": 1.2116275614449664e+16,
|
104 |
+
"train_loss": 0.0,
|
105 |
+
"train_runtime": 1714.5809,
|
106 |
+
"train_samples_per_second": 1964.008,
|
107 |
+
"train_steps_per_second": 15.368
|
108 |
+
}
|
109 |
+
],
|
110 |
+
"max_steps": 26350,
|
111 |
+
"num_train_epochs": 50,
|
112 |
+
"total_flos": 1.2116275614449664e+16,
|
113 |
+
"trial_name": null,
|
114 |
+
"trial_params": null
|
115 |
+
}
|