End of training
Browse files- README.md +14 -2
- all_results.json +13 -13
- eval_results.json +9 -9
- train_results.json +4 -4
- trainer_state.json +51 -51
README.md
CHANGED
@@ -3,11 +3,23 @@ license: mit
|
|
3 |
base_model: facebook/bart-large-cnn
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
metrics:
|
7 |
- rouge
|
8 |
model-index:
|
9 |
- name: pep_summarization
|
10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -15,7 +27,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# pep_summarization
|
17 |
|
18 |
-
This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.1242
|
21 |
- Rouge1: 75.3806
|
|
|
3 |
base_model: facebook/bart-large-cnn
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- fedora-copr/pep-sum
|
8 |
metrics:
|
9 |
- rouge
|
10 |
model-index:
|
11 |
- name: pep_summarization
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Summarization
|
15 |
+
type: summarization
|
16 |
+
dataset:
|
17 |
+
name: fedora-copr/pep-sum
|
18 |
+
type: fedora-copr/pep-sum
|
19 |
+
metrics:
|
20 |
+
- name: Rouge1
|
21 |
+
type: rouge
|
22 |
+
value: 75.3806
|
23 |
---
|
24 |
|
25 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
27 |
|
28 |
# pep_summarization
|
29 |
|
30 |
+
This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the fedora-copr/pep-sum dataset.
|
31 |
It achieves the following results on the evaluation set:
|
32 |
- Loss: 0.1242
|
33 |
- Rouge1: 75.3806
|
all_results.json
CHANGED
@@ -1,18 +1,18 @@
|
|
1 |
{
|
2 |
"epoch": 5.0,
|
3 |
-
"eval_gen_len":
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_rouge1":
|
6 |
-
"eval_rouge2":
|
7 |
-
"eval_rougeL":
|
8 |
-
"eval_rougeLsum":
|
9 |
-
"eval_runtime":
|
10 |
"eval_samples": 69,
|
11 |
-
"eval_samples_per_second":
|
12 |
-
"eval_steps_per_second": 1.
|
13 |
-
"train_loss": 0.
|
14 |
-
"train_runtime":
|
15 |
"train_samples": 276,
|
16 |
-
"train_samples_per_second":
|
17 |
-
"train_steps_per_second":
|
18 |
}
|
|
|
1 |
{
|
2 |
"epoch": 5.0,
|
3 |
+
"eval_gen_len": 85.31884057971014,
|
4 |
+
"eval_loss": 0.12416736036539078,
|
5 |
+
"eval_rouge1": 75.3806,
|
6 |
+
"eval_rouge2": 74.6735,
|
7 |
+
"eval_rougeL": 75.5866,
|
8 |
+
"eval_rougeLsum": 75.5446,
|
9 |
+
"eval_runtime": 11.3295,
|
10 |
"eval_samples": 69,
|
11 |
+
"eval_samples_per_second": 6.09,
|
12 |
+
"eval_steps_per_second": 1.589,
|
13 |
+
"train_loss": 0.036720043679942256,
|
14 |
+
"train_runtime": 132.663,
|
15 |
"train_samples": 276,
|
16 |
+
"train_samples_per_second": 10.402,
|
17 |
+
"train_steps_per_second": 2.601
|
18 |
}
|
eval_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
"epoch": 5.0,
|
3 |
-
"eval_gen_len":
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_rouge1":
|
6 |
-
"eval_rouge2":
|
7 |
-
"eval_rougeL":
|
8 |
-
"eval_rougeLsum":
|
9 |
-
"eval_runtime":
|
10 |
"eval_samples": 69,
|
11 |
-
"eval_samples_per_second":
|
12 |
-
"eval_steps_per_second": 1.
|
13 |
}
|
|
|
1 |
{
|
2 |
"epoch": 5.0,
|
3 |
+
"eval_gen_len": 85.31884057971014,
|
4 |
+
"eval_loss": 0.12416736036539078,
|
5 |
+
"eval_rouge1": 75.3806,
|
6 |
+
"eval_rouge2": 74.6735,
|
7 |
+
"eval_rougeL": 75.5866,
|
8 |
+
"eval_rougeLsum": 75.5446,
|
9 |
+
"eval_runtime": 11.3295,
|
10 |
"eval_samples": 69,
|
11 |
+
"eval_samples_per_second": 6.09,
|
12 |
+
"eval_steps_per_second": 1.589
|
13 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 5.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 276,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 5.0,
|
3 |
+
"train_loss": 0.036720043679942256,
|
4 |
+
"train_runtime": 132.663,
|
5 |
"train_samples": 276,
|
6 |
+
"train_samples_per_second": 10.402,
|
7 |
+
"train_steps_per_second": 2.601
|
8 |
}
|
trainer_state.json
CHANGED
@@ -10,77 +10,77 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_gen_len":
|
14 |
-
"eval_loss": 0.
|
15 |
-
"eval_rouge1":
|
16 |
-
"eval_rouge2":
|
17 |
-
"eval_rougeL":
|
18 |
-
"eval_rougeLsum":
|
19 |
-
"eval_runtime":
|
20 |
-
"eval_samples_per_second":
|
21 |
-
"eval_steps_per_second": 1.
|
22 |
"step": 69
|
23 |
},
|
24 |
{
|
25 |
"epoch": 2.0,
|
26 |
-
"eval_gen_len":
|
27 |
-
"eval_loss": 0.
|
28 |
-
"eval_rouge1":
|
29 |
-
"eval_rouge2":
|
30 |
-
"eval_rougeL":
|
31 |
-
"eval_rougeLsum":
|
32 |
-
"eval_runtime":
|
33 |
-
"eval_samples_per_second":
|
34 |
-
"eval_steps_per_second": 1.
|
35 |
"step": 138
|
36 |
},
|
37 |
{
|
38 |
"epoch": 3.0,
|
39 |
-
"eval_gen_len":
|
40 |
-
"eval_loss": 0.
|
41 |
-
"eval_rouge1":
|
42 |
-
"eval_rouge2":
|
43 |
-
"eval_rougeL":
|
44 |
-
"eval_rougeLsum":
|
45 |
-
"eval_runtime":
|
46 |
-
"eval_samples_per_second":
|
47 |
-
"eval_steps_per_second": 1.
|
48 |
"step": 207
|
49 |
},
|
50 |
{
|
51 |
"epoch": 4.0,
|
52 |
-
"eval_gen_len":
|
53 |
-
"eval_loss": 0.
|
54 |
-
"eval_rouge1":
|
55 |
-
"eval_rouge2":
|
56 |
-
"eval_rougeL":
|
57 |
-
"eval_rougeLsum":
|
58 |
-
"eval_runtime":
|
59 |
-
"eval_samples_per_second":
|
60 |
-
"eval_steps_per_second": 1.
|
61 |
"step": 276
|
62 |
},
|
63 |
{
|
64 |
"epoch": 5.0,
|
65 |
-
"eval_gen_len":
|
66 |
-
"eval_loss": 0.
|
67 |
-
"eval_rouge1":
|
68 |
-
"eval_rouge2":
|
69 |
-
"eval_rougeL":
|
70 |
-
"eval_rougeLsum":
|
71 |
-
"eval_runtime":
|
72 |
-
"eval_samples_per_second":
|
73 |
-
"eval_steps_per_second": 1.
|
74 |
"step": 345
|
75 |
},
|
76 |
{
|
77 |
"epoch": 5.0,
|
78 |
"step": 345,
|
79 |
-
"total_flos":
|
80 |
-
"train_loss": 0.
|
81 |
-
"train_runtime":
|
82 |
-
"train_samples_per_second":
|
83 |
-
"train_steps_per_second":
|
84 |
}
|
85 |
],
|
86 |
"logging_steps": 500,
|
@@ -88,7 +88,7 @@
|
|
88 |
"num_input_tokens_seen": 0,
|
89 |
"num_train_epochs": 5,
|
90 |
"save_steps": 500,
|
91 |
-
"total_flos":
|
92 |
"train_batch_size": 4,
|
93 |
"trial_name": null,
|
94 |
"trial_params": null
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_gen_len": 95.44927536231884,
|
14 |
+
"eval_loss": 0.09570997208356857,
|
15 |
+
"eval_rouge1": 72.6601,
|
16 |
+
"eval_rouge2": 71.6824,
|
17 |
+
"eval_rougeL": 72.6858,
|
18 |
+
"eval_rougeLsum": 72.4668,
|
19 |
+
"eval_runtime": 12.0064,
|
20 |
+
"eval_samples_per_second": 5.747,
|
21 |
+
"eval_steps_per_second": 1.499,
|
22 |
"step": 69
|
23 |
},
|
24 |
{
|
25 |
"epoch": 2.0,
|
26 |
+
"eval_gen_len": 92.01449275362319,
|
27 |
+
"eval_loss": 0.13447459042072296,
|
28 |
+
"eval_rouge1": 75.0063,
|
29 |
+
"eval_rouge2": 74.0782,
|
30 |
+
"eval_rougeL": 75.0597,
|
31 |
+
"eval_rougeLsum": 74.8943,
|
32 |
+
"eval_runtime": 11.945,
|
33 |
+
"eval_samples_per_second": 5.776,
|
34 |
+
"eval_steps_per_second": 1.507,
|
35 |
"step": 138
|
36 |
},
|
37 |
{
|
38 |
"epoch": 3.0,
|
39 |
+
"eval_gen_len": 85.46376811594203,
|
40 |
+
"eval_loss": 0.14119356870651245,
|
41 |
+
"eval_rouge1": 75.3012,
|
42 |
+
"eval_rouge2": 74.5492,
|
43 |
+
"eval_rougeL": 75.4246,
|
44 |
+
"eval_rougeLsum": 75.324,
|
45 |
+
"eval_runtime": 10.9494,
|
46 |
+
"eval_samples_per_second": 6.302,
|
47 |
+
"eval_steps_per_second": 1.644,
|
48 |
"step": 207
|
49 |
},
|
50 |
{
|
51 |
"epoch": 4.0,
|
52 |
+
"eval_gen_len": 85.04347826086956,
|
53 |
+
"eval_loss": 0.10889122635126114,
|
54 |
+
"eval_rouge1": 74.8426,
|
55 |
+
"eval_rouge2": 74.0317,
|
56 |
+
"eval_rougeL": 74.8939,
|
57 |
+
"eval_rougeLsum": 74.8128,
|
58 |
+
"eval_runtime": 11.2109,
|
59 |
+
"eval_samples_per_second": 6.155,
|
60 |
+
"eval_steps_per_second": 1.606,
|
61 |
"step": 276
|
62 |
},
|
63 |
{
|
64 |
"epoch": 5.0,
|
65 |
+
"eval_gen_len": 85.31884057971014,
|
66 |
+
"eval_loss": 0.12416736036539078,
|
67 |
+
"eval_rouge1": 75.3806,
|
68 |
+
"eval_rouge2": 74.6735,
|
69 |
+
"eval_rougeL": 75.5866,
|
70 |
+
"eval_rougeLsum": 75.5446,
|
71 |
+
"eval_runtime": 11.151,
|
72 |
+
"eval_samples_per_second": 6.188,
|
73 |
+
"eval_steps_per_second": 1.614,
|
74 |
"step": 345
|
75 |
},
|
76 |
{
|
77 |
"epoch": 5.0,
|
78 |
"step": 345,
|
79 |
+
"total_flos": 2990604350914560.0,
|
80 |
+
"train_loss": 0.036720043679942256,
|
81 |
+
"train_runtime": 132.663,
|
82 |
+
"train_samples_per_second": 10.402,
|
83 |
+
"train_steps_per_second": 2.601
|
84 |
}
|
85 |
],
|
86 |
"logging_steps": 500,
|
|
|
88 |
"num_input_tokens_seen": 0,
|
89 |
"num_train_epochs": 5,
|
90 |
"save_steps": 500,
|
91 |
+
"total_flos": 2990604350914560.0,
|
92 |
"train_batch_size": 4,
|
93 |
"trial_name": null,
|
94 |
"trial_params": null
|