JennnDexter
commited on
Commit
•
d89141a
1
Parent(s):
d886531
End of training
Browse files- README.md +4 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +70 -0
README.md
CHANGED
@@ -1,4 +1,7 @@
|
|
1 |
---
|
|
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: t5-small
|
4 |
tags:
|
@@ -15,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# Translation
|
17 |
|
18 |
-
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the opus_books dataset.
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
- fr
|
5 |
license: apache-2.0
|
6 |
base_model: t5-small
|
7 |
tags:
|
|
|
18 |
|
19 |
# Translation
|
20 |
|
21 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the opus_books en-fr dataset.
|
22 |
|
23 |
## Model description
|
24 |
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 1.8941770739472503,
|
4 |
+
"train_runtime": 1134.2734,
|
5 |
+
"train_samples": 127085,
|
6 |
+
"train_samples_per_second": 112.041,
|
7 |
+
"train_steps_per_second": 3.501
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 1.8941770739472503,
|
4 |
+
"train_runtime": 1134.2734,
|
5 |
+
"train_samples": 127085,
|
6 |
+
"train_samples_per_second": 112.041,
|
7 |
+
"train_steps_per_second": 3.501
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9998741029837593,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 3971,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.13,
|
13 |
+
"learning_rate": 4.370435658524301e-05,
|
14 |
+
"loss": 2.0905,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.25,
|
19 |
+
"learning_rate": 3.740871317048602e-05,
|
20 |
+
"loss": 1.9275,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.38,
|
25 |
+
"learning_rate": 3.111306975572904e-05,
|
26 |
+
"loss": 1.893,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.5,
|
31 |
+
"learning_rate": 2.481742634097205e-05,
|
32 |
+
"loss": 1.8706,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.63,
|
37 |
+
"learning_rate": 1.8521782926215058e-05,
|
38 |
+
"loss": 1.8604,
|
39 |
+
"step": 2500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.76,
|
43 |
+
"learning_rate": 1.2226139511458072e-05,
|
44 |
+
"loss": 1.8527,
|
45 |
+
"step": 3000
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.88,
|
49 |
+
"learning_rate": 5.930496096701083e-06,
|
50 |
+
"loss": 1.8332,
|
51 |
+
"step": 3500
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.0,
|
55 |
+
"step": 3971,
|
56 |
+
"total_flos": 3541933009403904.0,
|
57 |
+
"train_loss": 1.8941770739472503,
|
58 |
+
"train_runtime": 1134.2734,
|
59 |
+
"train_samples_per_second": 112.041,
|
60 |
+
"train_steps_per_second": 3.501
|
61 |
+
}
|
62 |
+
],
|
63 |
+
"logging_steps": 500,
|
64 |
+
"max_steps": 3971,
|
65 |
+
"num_train_epochs": 1,
|
66 |
+
"save_steps": 200,
|
67 |
+
"total_flos": 3541933009403904.0,
|
68 |
+
"trial_name": null,
|
69 |
+
"trial_params": null
|
70 |
+
}
|