indiejoseph
commited on
Commit
•
516fc8d
1
Parent(s):
a7f5baf
End of training
Browse files- README.md +7 -1
- all_results.json +15 -0
- eval_results.json +10 -0
- train_results.json +8 -0
- trainer_state.json +82 -0
README.md
CHANGED
@@ -1,6 +1,9 @@
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
|
|
|
|
4 |
model-index:
|
5 |
- name: bart-base-cantonese
|
6 |
results: []
|
@@ -11,7 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
11 |
|
12 |
# bart-base-cantonese
|
13 |
|
14 |
-
This model
|
|
|
|
|
|
|
15 |
|
16 |
## Model description
|
17 |
|
|
|
1 |
---
|
2 |
+
base_model: /notebooks/cantonese/bart-base-chinese
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
model-index:
|
8 |
- name: bart-base-cantonese
|
9 |
results: []
|
|
|
14 |
|
15 |
# bart-base-cantonese
|
16 |
|
17 |
+
This model is a fine-tuned version of [/notebooks/cantonese/bart-base-chinese](https://huggingface.co//notebooks/cantonese/bart-base-chinese) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.8513
|
20 |
+
- Accuracy: 0.8363
|
21 |
|
22 |
## Model description
|
23 |
|
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.8363284200339879,
|
4 |
+
"eval_loss": 0.8513006567955017,
|
5 |
+
"eval_runtime": 42.815,
|
6 |
+
"eval_samples": 1324,
|
7 |
+
"eval_samples_per_second": 30.924,
|
8 |
+
"eval_steps_per_second": 1.939,
|
9 |
+
"perplexity": 2.3426919093610663,
|
10 |
+
"train_loss": 1.0451076868909677,
|
11 |
+
"train_runtime": 3967.7657,
|
12 |
+
"train_samples": 25155,
|
13 |
+
"train_samples_per_second": 19.02,
|
14 |
+
"train_steps_per_second": 1.189
|
15 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.8363284200339879,
|
4 |
+
"eval_loss": 0.8513006567955017,
|
5 |
+
"eval_runtime": 42.815,
|
6 |
+
"eval_samples": 1324,
|
7 |
+
"eval_samples_per_second": 30.924,
|
8 |
+
"eval_steps_per_second": 1.939,
|
9 |
+
"perplexity": 2.3426919093610663
|
10 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 1.0451076868909677,
|
4 |
+
"train_runtime": 3967.7657,
|
5 |
+
"train_samples": 25155,
|
6 |
+
"train_samples_per_second": 19.02,
|
7 |
+
"train_steps_per_second": 1.189
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 2000.0,
|
6 |
+
"global_step": 4719,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.32,
|
13 |
+
"learning_rate": 2.5e-05,
|
14 |
+
"loss": 1.5255,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.64,
|
19 |
+
"learning_rate": 5e-05,
|
20 |
+
"loss": 1.1342,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.95,
|
25 |
+
"learning_rate": 7.500000000000001e-05,
|
26 |
+
"loss": 1.0615,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 1.27,
|
31 |
+
"learning_rate": 0.0001,
|
32 |
+
"loss": 1.021,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 1.59,
|
37 |
+
"learning_rate": 8.161088635527768e-05,
|
38 |
+
"loss": 0.9927,
|
39 |
+
"step": 2500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.91,
|
43 |
+
"learning_rate": 6.322177271055535e-05,
|
44 |
+
"loss": 0.9672,
|
45 |
+
"step": 3000
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 2.23,
|
49 |
+
"learning_rate": 4.483265906583303e-05,
|
50 |
+
"loss": 0.9361,
|
51 |
+
"step": 3500
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 2.54,
|
55 |
+
"learning_rate": 2.6443545421110705e-05,
|
56 |
+
"loss": 0.9202,
|
57 |
+
"step": 4000
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 2.86,
|
61 |
+
"learning_rate": 8.054431776388379e-06,
|
62 |
+
"loss": 0.9096,
|
63 |
+
"step": 4500
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 3.0,
|
67 |
+
"step": 4719,
|
68 |
+
"total_flos": 2.30068809105408e+16,
|
69 |
+
"train_loss": 1.0451076868909677,
|
70 |
+
"train_runtime": 3967.7657,
|
71 |
+
"train_samples_per_second": 19.02,
|
72 |
+
"train_steps_per_second": 1.189
|
73 |
+
}
|
74 |
+
],
|
75 |
+
"logging_steps": 500,
|
76 |
+
"max_steps": 4719,
|
77 |
+
"num_train_epochs": 3,
|
78 |
+
"save_steps": 2000,
|
79 |
+
"total_flos": 2.30068809105408e+16,
|
80 |
+
"trial_name": null,
|
81 |
+
"trial_params": null
|
82 |
+
}
|