End of training
Browse files- README.md +3 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +36 -0
README.md
CHANGED
@@ -3,6 +3,8 @@ license: apache-2.0
|
|
3 |
base_model: google/mt5-small
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: formatted_addr
|
8 |
results: []
|
@@ -13,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# formatted_addr
|
15 |
|
16 |
-
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
3 |
base_model: google/mt5-small
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- cwchang/tw_address_small
|
8 |
model-index:
|
9 |
- name: formatted_addr
|
10 |
results: []
|
|
|
15 |
|
16 |
# formatted_addr
|
17 |
|
18 |
+
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the cwchang/tw_address_small dataset.
|
19 |
|
20 |
## Model description
|
21 |
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 11.181663004557292,
|
4 |
+
"train_runtime": 140.1775,
|
5 |
+
"train_samples": 800,
|
6 |
+
"train_samples_per_second": 17.121,
|
7 |
+
"train_steps_per_second": 4.28
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 11.181663004557292,
|
4 |
+
"train_runtime": 140.1775,
|
5 |
+
"train_samples": 800,
|
6 |
+
"train_samples_per_second": 17.121,
|
7 |
+
"train_steps_per_second": 4.28
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 600,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 2.5,
|
13 |
+
"learning_rate": 8.333333333333334e-06,
|
14 |
+
"loss": 12.2245,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 3.0,
|
19 |
+
"step": 600,
|
20 |
+
"total_flos": 17349599232000.0,
|
21 |
+
"train_loss": 11.181663004557292,
|
22 |
+
"train_runtime": 140.1775,
|
23 |
+
"train_samples_per_second": 17.121,
|
24 |
+
"train_steps_per_second": 4.28
|
25 |
+
}
|
26 |
+
],
|
27 |
+
"logging_steps": 500,
|
28 |
+
"max_steps": 600,
|
29 |
+
"num_input_tokens_seen": 0,
|
30 |
+
"num_train_epochs": 3,
|
31 |
+
"save_steps": 500,
|
32 |
+
"total_flos": 17349599232000.0,
|
33 |
+
"train_batch_size": 4,
|
34 |
+
"trial_name": null,
|
35 |
+
"trial_params": null
|
36 |
+
}
|