Commit
•
6c571d1
1
Parent(s):
f0f1a7b
End of training
Browse files- all_results.json +8 -8
- eval_results.json +4 -4
- pytorch_model.bin +1 -1
- run.sh +4 -3
- special_tokens_map.json +1 -1
- train_results.json +5 -5
- trainer_state.json +11 -11
- training_args.bin +1 -1
all_results.json
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
{
|
2 |
-
"epoch": 0
|
3 |
"eval_loss": Infinity,
|
4 |
-
"eval_runtime":
|
5 |
"eval_samples": 301,
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 3.
|
8 |
"eval_wer": 1.0,
|
9 |
-
"train_loss":
|
10 |
-
"train_runtime":
|
11 |
"train_samples": 704,
|
12 |
-
"train_samples_per_second":
|
13 |
-
"train_steps_per_second":
|
14 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 1.0,
|
3 |
"eval_loss": Infinity,
|
4 |
+
"eval_runtime": 10.8674,
|
5 |
"eval_samples": 301,
|
6 |
+
"eval_samples_per_second": 27.697,
|
7 |
+
"eval_steps_per_second": 3.497,
|
8 |
"eval_wer": 1.0,
|
9 |
+
"train_loss": 4.538612365722656,
|
10 |
+
"train_runtime": 34.6,
|
11 |
"train_samples": 704,
|
12 |
+
"train_samples_per_second": 20.347,
|
13 |
+
"train_steps_per_second": 2.543
|
14 |
}
|
eval_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"epoch": 0
|
3 |
"eval_loss": Infinity,
|
4 |
-
"eval_runtime":
|
5 |
"eval_samples": 301,
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 3.
|
8 |
"eval_wer": 1.0
|
9 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 1.0,
|
3 |
"eval_loss": Infinity,
|
4 |
+
"eval_runtime": 10.8674,
|
5 |
"eval_samples": 301,
|
6 |
+
"eval_samples_per_second": 27.697,
|
7 |
+
"eval_steps_per_second": 3.497,
|
8 |
"eval_wer": 1.0
|
9 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1247823
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:612dd692031680aae02deafa36c7fa8dadce27d4b31ce9acb75461c1e48b9ddb
|
3 |
size 1247823
|
run.sh
CHANGED
@@ -4,14 +4,15 @@ python run_speech_recognition_ctc.py \
|
|
4 |
--dataset_config_name="ab" \
|
5 |
--output_dir="./" \
|
6 |
--overwrite_output_dir \
|
7 |
-
--
|
8 |
-
--
|
|
|
|
|
9 |
--learning_rate="3e-4" \
|
10 |
--save_total_limit="1" \
|
11 |
--evaluation_strategy="steps" \
|
12 |
--text_column_name="sentence" \
|
13 |
--length_column_name="input_length" \
|
14 |
-
--save_steps="5" \
|
15 |
--layerdrop="0.0" \
|
16 |
--freeze_feature_encoder \
|
17 |
--gradient_checkpointing \
|
|
|
4 |
--dataset_config_name="ab" \
|
5 |
--output_dir="./" \
|
6 |
--overwrite_output_dir \
|
7 |
+
--num_train_epochs="1" \
|
8 |
+
--save_steps="100" \
|
9 |
+
--eval_steps="500" \
|
10 |
+
--per_device_train_batch_size="8" \
|
11 |
--learning_rate="3e-4" \
|
12 |
--save_total_limit="1" \
|
13 |
--evaluation_strategy="steps" \
|
14 |
--text_column_name="sentence" \
|
15 |
--length_column_name="input_length" \
|
|
|
16 |
--layerdrop="0.0" \
|
17 |
--freeze_feature_encoder \
|
18 |
--gradient_checkpointing \
|
special_tokens_map.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch": 0
|
3 |
-
"train_loss":
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 704,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 4.538612365722656,
|
4 |
+
"train_runtime": 34.6,
|
5 |
"train_samples": 704,
|
6 |
+
"train_samples_per_second": 20.347,
|
7 |
+
"train_steps_per_second": 2.543
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,25 +1,25 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
-
"epoch": 0
|
12 |
-
"step":
|
13 |
-
"total_flos":
|
14 |
-
"train_loss":
|
15 |
-
"train_runtime":
|
16 |
-
"train_samples_per_second":
|
17 |
-
"train_steps_per_second":
|
18 |
}
|
19 |
],
|
20 |
-
"max_steps":
|
21 |
"num_train_epochs": 1,
|
22 |
-
"total_flos":
|
23 |
"trial_name": null,
|
24 |
"trial_params": null
|
25 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 88,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"step": 88,
|
13 |
+
"total_flos": 130613499224064.0,
|
14 |
+
"train_loss": 4.538612365722656,
|
15 |
+
"train_runtime": 34.6,
|
16 |
+
"train_samples_per_second": 20.347,
|
17 |
+
"train_steps_per_second": 2.543
|
18 |
}
|
19 |
],
|
20 |
+
"max_steps": 88,
|
21 |
"num_train_epochs": 1,
|
22 |
+
"total_flos": 130613499224064.0,
|
23 |
"trial_name": null,
|
24 |
"trial_params": null
|
25 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2991
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20957f7464463ef438ad81644f984c525e32f342ea8286c481883de4c457daef
|
3 |
size 2991
|