End of training
Browse files- README.md +3 -1
- all_results.json +4 -4
- train_results.json +4 -4
- trainer_state.json +7 -7
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
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 800,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 4.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"train_loss": 6.107138163248698,
|
| 4 |
+
"train_runtime": 143.5946,
|
| 5 |
"train_samples": 800,
|
| 6 |
+
"train_samples_per_second": 16.714,
|
| 7 |
+
"train_steps_per_second": 4.178
|
| 8 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 800,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 4.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"train_loss": 6.107138163248698,
|
| 4 |
+
"train_runtime": 143.5946,
|
| 5 |
"train_samples": 800,
|
| 6 |
+
"train_samples_per_second": 16.714,
|
| 7 |
+
"train_steps_per_second": 4.178
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -11,17 +11,17 @@
|
|
| 11 |
{
|
| 12 |
"epoch": 2.5,
|
| 13 |
"learning_rate": 8.333333333333334e-06,
|
| 14 |
-
"loss":
|
| 15 |
"step": 500
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 3.0,
|
| 19 |
"step": 600,
|
| 20 |
-
"total_flos":
|
| 21 |
-
"train_loss":
|
| 22 |
-
"train_runtime":
|
| 23 |
-
"train_samples_per_second":
|
| 24 |
-
"train_steps_per_second": 4.
|
| 25 |
}
|
| 26 |
],
|
| 27 |
"logging_steps": 500,
|
|
@@ -29,7 +29,7 @@
|
|
| 29 |
"num_input_tokens_seen": 0,
|
| 30 |
"num_train_epochs": 3,
|
| 31 |
"save_steps": 500,
|
| 32 |
-
"total_flos":
|
| 33 |
"train_batch_size": 4,
|
| 34 |
"trial_name": null,
|
| 35 |
"trial_params": null
|
|
|
|
| 11 |
{
|
| 12 |
"epoch": 2.5,
|
| 13 |
"learning_rate": 8.333333333333334e-06,
|
| 14 |
+
"loss": 6.9234,
|
| 15 |
"step": 500
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 3.0,
|
| 19 |
"step": 600,
|
| 20 |
+
"total_flos": 52647771955200.0,
|
| 21 |
+
"train_loss": 6.107138163248698,
|
| 22 |
+
"train_runtime": 143.5946,
|
| 23 |
+
"train_samples_per_second": 16.714,
|
| 24 |
+
"train_steps_per_second": 4.178
|
| 25 |
}
|
| 26 |
],
|
| 27 |
"logging_steps": 500,
|
|
|
|
| 29 |
"num_input_tokens_seen": 0,
|
| 30 |
"num_train_epochs": 3,
|
| 31 |
"save_steps": 500,
|
| 32 |
+
"total_flos": 52647771955200.0,
|
| 33 |
"train_batch_size": 4,
|
| 34 |
"trial_name": null,
|
| 35 |
"trial_params": null
|