Commit
•
1b22227
1
Parent(s):
8f63fa2
Adding model files
Browse files- README.md +75 -3
- added_tokens.json +1 -0
- all_results.json +14 -0
- checkpoint-6150/config.json +107 -0
- checkpoint-6150/optimizer.pt +3 -0
- checkpoint-6150/preprocessor_config.json +9 -0
- checkpoint-6150/pytorch_model.bin +3 -0
- checkpoint-6150/rng_state.pth +3 -0
- checkpoint-6150/scaler.pt +3 -0
- checkpoint-6150/scheduler.pt +3 -0
- checkpoint-6150/trainer_state.json +196 -0
- checkpoint-6150/training_args.bin +3 -0
- config.json +107 -0
- eval_results.json +9 -0
- preprocessor_config.json +9 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +205 -0
- training_args.bin +3 -0
- vocab.json +1 -0
README.md
CHANGED
|
@@ -1,3 +1,75 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- fr
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- automatic-speech-recognition
|
| 7 |
+
- common_voice
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
datasets:
|
| 10 |
+
- common_voice
|
| 11 |
+
model-index:
|
| 12 |
+
- name: wav2vec2-cls-r-300m-fr
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# wav2vec2-cls-r-300m-fr
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the COMMON_VOICE - FR dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.6521
|
| 24 |
+
- Wer: 0.4330
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 0.0003
|
| 44 |
+
- train_batch_size: 16
|
| 45 |
+
- eval_batch_size: 8
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 10.0
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 56 |
+
| 2.6773 | 0.8 | 500 | 1.3907 | 0.9864 |
|
| 57 |
+
| 0.9526 | 1.6 | 1000 | 0.7760 | 0.6448 |
|
| 58 |
+
| 0.6418 | 2.4 | 1500 | 0.7605 | 0.6194 |
|
| 59 |
+
| 0.5028 | 3.2 | 2000 | 0.6516 | 0.5322 |
|
| 60 |
+
| 0.4133 | 4.0 | 2500 | 0.6303 | 0.5097 |
|
| 61 |
+
| 0.3285 | 4.8 | 3000 | 0.6422 | 0.5062 |
|
| 62 |
+
| 0.2764 | 5.6 | 3500 | 0.5936 | 0.4748 |
|
| 63 |
+
| 0.2361 | 6.4 | 4000 | 0.6486 | 0.4683 |
|
| 64 |
+
| 0.2049 | 7.2 | 4500 | 0.6321 | 0.4532 |
|
| 65 |
+
| 0.176 | 8.0 | 5000 | 0.6230 | 0.4482 |
|
| 66 |
+
| 0.1393 | 8.8 | 5500 | 0.6595 | 0.4403 |
|
| 67 |
+
| 0.1141 | 9.6 | 6000 | 0.6552 | 0.4348 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.17.0.dev0
|
| 73 |
+
- Pytorch 1.10.2+cu102
|
| 74 |
+
- Datasets 1.18.2.dev0
|
| 75 |
+
- Tokenizers 0.11.0
|
added_tokens.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"<s>": 98, "</s>": 99}
|
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 0.6521482467651367,
|
| 4 |
+
"eval_runtime": 218.1002,
|
| 5 |
+
"eval_samples": 5000,
|
| 6 |
+
"eval_samples_per_second": 22.925,
|
| 7 |
+
"eval_steps_per_second": 2.866,
|
| 8 |
+
"eval_wer": 0.43299040254091004,
|
| 9 |
+
"train_loss": 0.5376352182006836,
|
| 10 |
+
"train_runtime": 6902.5833,
|
| 11 |
+
"train_samples": 10000,
|
| 12 |
+
"train_samples_per_second": 14.487,
|
| 13 |
+
"train_steps_per_second": 0.905
|
| 14 |
+
}
|
checkpoint-6150/config.json
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/wav2vec2-xls-r-300m",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"adapter_kernel_size": 3,
|
| 5 |
+
"adapter_stride": 2,
|
| 6 |
+
"add_adapter": false,
|
| 7 |
+
"apply_spec_augment": true,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"Wav2Vec2ForCTC"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"bos_token_id": 1,
|
| 13 |
+
"classifier_proj_size": 256,
|
| 14 |
+
"codevector_dim": 768,
|
| 15 |
+
"contrastive_logits_temperature": 0.1,
|
| 16 |
+
"conv_bias": true,
|
| 17 |
+
"conv_dim": [
|
| 18 |
+
512,
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512
|
| 25 |
+
],
|
| 26 |
+
"conv_kernel": [
|
| 27 |
+
10,
|
| 28 |
+
3,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
2,
|
| 33 |
+
2
|
| 34 |
+
],
|
| 35 |
+
"conv_stride": [
|
| 36 |
+
5,
|
| 37 |
+
2,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2,
|
| 42 |
+
2
|
| 43 |
+
],
|
| 44 |
+
"ctc_loss_reduction": "mean",
|
| 45 |
+
"ctc_zero_infinity": false,
|
| 46 |
+
"diversity_loss_weight": 0.1,
|
| 47 |
+
"do_stable_layer_norm": true,
|
| 48 |
+
"eos_token_id": 2,
|
| 49 |
+
"feat_extract_activation": "gelu",
|
| 50 |
+
"feat_extract_dropout": 0.0,
|
| 51 |
+
"feat_extract_norm": "layer",
|
| 52 |
+
"feat_proj_dropout": 0.0,
|
| 53 |
+
"feat_quantizer_dropout": 0.0,
|
| 54 |
+
"final_dropout": 0.0,
|
| 55 |
+
"hidden_act": "gelu",
|
| 56 |
+
"hidden_dropout": 0.0,
|
| 57 |
+
"hidden_size": 1024,
|
| 58 |
+
"initializer_range": 0.02,
|
| 59 |
+
"intermediate_size": 4096,
|
| 60 |
+
"layer_norm_eps": 1e-05,
|
| 61 |
+
"layerdrop": 0.0,
|
| 62 |
+
"mask_feature_length": 10,
|
| 63 |
+
"mask_feature_min_masks": 0,
|
| 64 |
+
"mask_feature_prob": 0.0,
|
| 65 |
+
"mask_time_length": 10,
|
| 66 |
+
"mask_time_min_masks": 2,
|
| 67 |
+
"mask_time_prob": 0.05,
|
| 68 |
+
"model_type": "wav2vec2",
|
| 69 |
+
"num_adapter_layers": 3,
|
| 70 |
+
"num_attention_heads": 16,
|
| 71 |
+
"num_codevector_groups": 2,
|
| 72 |
+
"num_codevectors_per_group": 320,
|
| 73 |
+
"num_conv_pos_embedding_groups": 16,
|
| 74 |
+
"num_conv_pos_embeddings": 128,
|
| 75 |
+
"num_feat_extract_layers": 7,
|
| 76 |
+
"num_hidden_layers": 24,
|
| 77 |
+
"num_negatives": 100,
|
| 78 |
+
"output_hidden_size": 1024,
|
| 79 |
+
"pad_token_id": 97,
|
| 80 |
+
"proj_codevector_dim": 768,
|
| 81 |
+
"tdnn_dilation": [
|
| 82 |
+
1,
|
| 83 |
+
2,
|
| 84 |
+
3,
|
| 85 |
+
1,
|
| 86 |
+
1
|
| 87 |
+
],
|
| 88 |
+
"tdnn_dim": [
|
| 89 |
+
512,
|
| 90 |
+
512,
|
| 91 |
+
512,
|
| 92 |
+
512,
|
| 93 |
+
1500
|
| 94 |
+
],
|
| 95 |
+
"tdnn_kernel": [
|
| 96 |
+
5,
|
| 97 |
+
3,
|
| 98 |
+
3,
|
| 99 |
+
1,
|
| 100 |
+
1
|
| 101 |
+
],
|
| 102 |
+
"torch_dtype": "float32",
|
| 103 |
+
"transformers_version": "4.17.0.dev0",
|
| 104 |
+
"use_weighted_layer_sum": false,
|
| 105 |
+
"vocab_size": 100,
|
| 106 |
+
"xvector_output_dim": 512
|
| 107 |
+
}
|
checkpoint-6150/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e391e5dad53b8b60bd8c4a460a7c1eabc540d5582ab892d1c343b9c3f6f4c02
|
| 3 |
+
size 2490878993
|
checkpoint-6150/preprocessor_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0,
|
| 7 |
+
"return_attention_mask": true,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|
checkpoint-6150/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59c9e0f83e7501c8783bd45d93ecd4209d484071c98d1f18a478a107dda79627
|
| 3 |
+
size 1262333681
|
checkpoint-6150/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39cba0a35f70c679ee24cbb51c03174b7983f412e9e4e73b301590c71c9f3731
|
| 3 |
+
size 14567
|
checkpoint-6150/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ff3aba594397e8587e51b929faa9fb4267682c4a88bb15276335b362cc33cf1
|
| 3 |
+
size 559
|
checkpoint-6150/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99462ccf6199e5f06244f5b4a9f506a469244bf1524a5410fc4bd4e3df533ea6
|
| 3 |
+
size 623
|
checkpoint-6150/trainer_state.json
ADDED
|
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.84,
|
| 5 |
+
"global_step": 6150,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.8,
|
| 12 |
+
"learning_rate": 0.000276096,
|
| 13 |
+
"loss": 2.6773,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.8,
|
| 18 |
+
"eval_loss": 1.390709400177002,
|
| 19 |
+
"eval_runtime": 221.8176,
|
| 20 |
+
"eval_samples_per_second": 22.541,
|
| 21 |
+
"eval_steps_per_second": 2.818,
|
| 22 |
+
"eval_wer": 0.9864438767290387,
|
| 23 |
+
"step": 500
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.6,
|
| 27 |
+
"learning_rate": 0.00025209599999999994,
|
| 28 |
+
"loss": 0.9526,
|
| 29 |
+
"step": 1000
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.6,
|
| 33 |
+
"eval_loss": 0.7760354280471802,
|
| 34 |
+
"eval_runtime": 219.0168,
|
| 35 |
+
"eval_samples_per_second": 22.829,
|
| 36 |
+
"eval_steps_per_second": 2.854,
|
| 37 |
+
"eval_wer": 0.644847982692352,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.4,
|
| 42 |
+
"learning_rate": 0.00022809599999999998,
|
| 43 |
+
"loss": 0.6418,
|
| 44 |
+
"step": 1500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 2.4,
|
| 48 |
+
"eval_loss": 0.760543942451477,
|
| 49 |
+
"eval_runtime": 217.3821,
|
| 50 |
+
"eval_samples_per_second": 23.001,
|
| 51 |
+
"eval_steps_per_second": 2.875,
|
| 52 |
+
"eval_wer": 0.6193928513889848,
|
| 53 |
+
"step": 1500
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 3.2,
|
| 57 |
+
"learning_rate": 0.000204096,
|
| 58 |
+
"loss": 0.5028,
|
| 59 |
+
"step": 2000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 3.2,
|
| 63 |
+
"eval_loss": 0.6515631675720215,
|
| 64 |
+
"eval_runtime": 217.5138,
|
| 65 |
+
"eval_samples_per_second": 22.987,
|
| 66 |
+
"eval_steps_per_second": 2.873,
|
| 67 |
+
"eval_wer": 0.532187161959999,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 4.0,
|
| 72 |
+
"learning_rate": 0.00018009599999999998,
|
| 73 |
+
"loss": 0.4133,
|
| 74 |
+
"step": 2500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 4.0,
|
| 78 |
+
"eval_loss": 0.630308210849762,
|
| 79 |
+
"eval_runtime": 220.9761,
|
| 80 |
+
"eval_samples_per_second": 22.627,
|
| 81 |
+
"eval_steps_per_second": 2.828,
|
| 82 |
+
"eval_wer": 0.5097010287923772,
|
| 83 |
+
"step": 2500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 4.8,
|
| 87 |
+
"learning_rate": 0.000156096,
|
| 88 |
+
"loss": 0.3285,
|
| 89 |
+
"step": 3000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 4.8,
|
| 93 |
+
"eval_loss": 0.6422050595283508,
|
| 94 |
+
"eval_runtime": 216.2337,
|
| 95 |
+
"eval_samples_per_second": 23.123,
|
| 96 |
+
"eval_steps_per_second": 2.89,
|
| 97 |
+
"eval_wer": 0.5062487053787199,
|
| 98 |
+
"step": 3000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 5.6,
|
| 102 |
+
"learning_rate": 0.00013209599999999998,
|
| 103 |
+
"loss": 0.2764,
|
| 104 |
+
"step": 3500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 5.6,
|
| 108 |
+
"eval_loss": 0.5936103463172913,
|
| 109 |
+
"eval_runtime": 221.9715,
|
| 110 |
+
"eval_samples_per_second": 22.525,
|
| 111 |
+
"eval_steps_per_second": 2.816,
|
| 112 |
+
"eval_wer": 0.47476351584616444,
|
| 113 |
+
"step": 3500
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 6.4,
|
| 117 |
+
"learning_rate": 0.00010809599999999998,
|
| 118 |
+
"loss": 0.2361,
|
| 119 |
+
"step": 4000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 6.4,
|
| 123 |
+
"eval_loss": 0.6486021280288696,
|
| 124 |
+
"eval_runtime": 217.2436,
|
| 125 |
+
"eval_samples_per_second": 23.016,
|
| 126 |
+
"eval_steps_per_second": 2.877,
|
| 127 |
+
"eval_wer": 0.4683191788073373,
|
| 128 |
+
"step": 4000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 7.2,
|
| 132 |
+
"learning_rate": 8.4144e-05,
|
| 133 |
+
"loss": 0.2049,
|
| 134 |
+
"step": 4500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 7.2,
|
| 138 |
+
"eval_loss": 0.6320939064025879,
|
| 139 |
+
"eval_runtime": 216.2222,
|
| 140 |
+
"eval_samples_per_second": 23.124,
|
| 141 |
+
"eval_steps_per_second": 2.891,
|
| 142 |
+
"eval_wer": 0.453198002255518,
|
| 143 |
+
"step": 4500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 8.0,
|
| 147 |
+
"learning_rate": 6.014399999999999e-05,
|
| 148 |
+
"loss": 0.176,
|
| 149 |
+
"step": 5000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"eval_loss": 0.6229676604270935,
|
| 154 |
+
"eval_runtime": 217.7281,
|
| 155 |
+
"eval_samples_per_second": 22.964,
|
| 156 |
+
"eval_steps_per_second": 2.871,
|
| 157 |
+
"eval_wer": 0.44822665653985133,
|
| 158 |
+
"step": 5000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 8.8,
|
| 162 |
+
"learning_rate": 3.6191999999999995e-05,
|
| 163 |
+
"loss": 0.1393,
|
| 164 |
+
"step": 5500
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 8.8,
|
| 168 |
+
"eval_loss": 0.6595410108566284,
|
| 169 |
+
"eval_runtime": 217.4753,
|
| 170 |
+
"eval_samples_per_second": 22.991,
|
| 171 |
+
"eval_steps_per_second": 2.874,
|
| 172 |
+
"eval_wer": 0.4402863126884393,
|
| 173 |
+
"step": 5500
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 9.6,
|
| 177 |
+
"learning_rate": 1.2192e-05,
|
| 178 |
+
"loss": 0.1141,
|
| 179 |
+
"step": 6000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 9.6,
|
| 183 |
+
"eval_loss": 0.6552333831787109,
|
| 184 |
+
"eval_runtime": 216.5487,
|
| 185 |
+
"eval_samples_per_second": 23.089,
|
| 186 |
+
"eval_steps_per_second": 2.886,
|
| 187 |
+
"eval_wer": 0.43480862620543625,
|
| 188 |
+
"step": 6000
|
| 189 |
+
}
|
| 190 |
+
],
|
| 191 |
+
"max_steps": 6250,
|
| 192 |
+
"num_train_epochs": 10,
|
| 193 |
+
"total_flos": 1.0577160442719683e+19,
|
| 194 |
+
"trial_name": null,
|
| 195 |
+
"trial_params": null
|
| 196 |
+
}
|
checkpoint-6150/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ca2ad775929458a40c80853a160c83c7e110384fc53cfba997ea42b133bea3d
|
| 3 |
+
size 3055
|
config.json
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/wav2vec2-xls-r-300m",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"adapter_kernel_size": 3,
|
| 5 |
+
"adapter_stride": 2,
|
| 6 |
+
"add_adapter": false,
|
| 7 |
+
"apply_spec_augment": true,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"Wav2Vec2ForCTC"
|
| 10 |
+
],
|
| 11 |
+
"attention_dropout": 0.0,
|
| 12 |
+
"bos_token_id": 1,
|
| 13 |
+
"classifier_proj_size": 256,
|
| 14 |
+
"codevector_dim": 768,
|
| 15 |
+
"contrastive_logits_temperature": 0.1,
|
| 16 |
+
"conv_bias": true,
|
| 17 |
+
"conv_dim": [
|
| 18 |
+
512,
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512
|
| 25 |
+
],
|
| 26 |
+
"conv_kernel": [
|
| 27 |
+
10,
|
| 28 |
+
3,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
2,
|
| 33 |
+
2
|
| 34 |
+
],
|
| 35 |
+
"conv_stride": [
|
| 36 |
+
5,
|
| 37 |
+
2,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2,
|
| 42 |
+
2
|
| 43 |
+
],
|
| 44 |
+
"ctc_loss_reduction": "mean",
|
| 45 |
+
"ctc_zero_infinity": false,
|
| 46 |
+
"diversity_loss_weight": 0.1,
|
| 47 |
+
"do_stable_layer_norm": true,
|
| 48 |
+
"eos_token_id": 2,
|
| 49 |
+
"feat_extract_activation": "gelu",
|
| 50 |
+
"feat_extract_dropout": 0.0,
|
| 51 |
+
"feat_extract_norm": "layer",
|
| 52 |
+
"feat_proj_dropout": 0.0,
|
| 53 |
+
"feat_quantizer_dropout": 0.0,
|
| 54 |
+
"final_dropout": 0.0,
|
| 55 |
+
"hidden_act": "gelu",
|
| 56 |
+
"hidden_dropout": 0.0,
|
| 57 |
+
"hidden_size": 1024,
|
| 58 |
+
"initializer_range": 0.02,
|
| 59 |
+
"intermediate_size": 4096,
|
| 60 |
+
"layer_norm_eps": 1e-05,
|
| 61 |
+
"layerdrop": 0.0,
|
| 62 |
+
"mask_feature_length": 10,
|
| 63 |
+
"mask_feature_min_masks": 0,
|
| 64 |
+
"mask_feature_prob": 0.0,
|
| 65 |
+
"mask_time_length": 10,
|
| 66 |
+
"mask_time_min_masks": 2,
|
| 67 |
+
"mask_time_prob": 0.05,
|
| 68 |
+
"model_type": "wav2vec2",
|
| 69 |
+
"num_adapter_layers": 3,
|
| 70 |
+
"num_attention_heads": 16,
|
| 71 |
+
"num_codevector_groups": 2,
|
| 72 |
+
"num_codevectors_per_group": 320,
|
| 73 |
+
"num_conv_pos_embedding_groups": 16,
|
| 74 |
+
"num_conv_pos_embeddings": 128,
|
| 75 |
+
"num_feat_extract_layers": 7,
|
| 76 |
+
"num_hidden_layers": 24,
|
| 77 |
+
"num_negatives": 100,
|
| 78 |
+
"output_hidden_size": 1024,
|
| 79 |
+
"pad_token_id": 97,
|
| 80 |
+
"proj_codevector_dim": 768,
|
| 81 |
+
"tdnn_dilation": [
|
| 82 |
+
1,
|
| 83 |
+
2,
|
| 84 |
+
3,
|
| 85 |
+
1,
|
| 86 |
+
1
|
| 87 |
+
],
|
| 88 |
+
"tdnn_dim": [
|
| 89 |
+
512,
|
| 90 |
+
512,
|
| 91 |
+
512,
|
| 92 |
+
512,
|
| 93 |
+
1500
|
| 94 |
+
],
|
| 95 |
+
"tdnn_kernel": [
|
| 96 |
+
5,
|
| 97 |
+
3,
|
| 98 |
+
3,
|
| 99 |
+
1,
|
| 100 |
+
1
|
| 101 |
+
],
|
| 102 |
+
"torch_dtype": "float32",
|
| 103 |
+
"transformers_version": "4.17.0.dev0",
|
| 104 |
+
"use_weighted_layer_sum": false,
|
| 105 |
+
"vocab_size": 100,
|
| 106 |
+
"xvector_output_dim": 512
|
| 107 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 0.6521482467651367,
|
| 4 |
+
"eval_runtime": 218.1002,
|
| 5 |
+
"eval_samples": 5000,
|
| 6 |
+
"eval_samples_per_second": 22.925,
|
| 7 |
+
"eval_steps_per_second": 2.866,
|
| 8 |
+
"eval_wer": 0.43299040254091004
|
| 9 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0,
|
| 7 |
+
"return_attention_mask": true,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f7098ad58c48ecfa8b6566c9e3a08616a070645236244ae70a2c46d15b4a8c0
|
| 3 |
+
size 1262333681
|
special_tokens_map.json
ADDED
|
@@ -0,0 +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}]}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./wav2vec2-cls-r-300m-fr", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.5376352182006836,
|
| 4 |
+
"train_runtime": 6902.5833,
|
| 5 |
+
"train_samples": 10000,
|
| 6 |
+
"train_samples_per_second": 14.487,
|
| 7 |
+
"train_steps_per_second": 0.905
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,205 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 6250,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.8,
|
| 12 |
+
"learning_rate": 0.000276096,
|
| 13 |
+
"loss": 2.6773,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.8,
|
| 18 |
+
"eval_loss": 1.390709400177002,
|
| 19 |
+
"eval_runtime": 221.8176,
|
| 20 |
+
"eval_samples_per_second": 22.541,
|
| 21 |
+
"eval_steps_per_second": 2.818,
|
| 22 |
+
"eval_wer": 0.9864438767290387,
|
| 23 |
+
"step": 500
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.6,
|
| 27 |
+
"learning_rate": 0.00025209599999999994,
|
| 28 |
+
"loss": 0.9526,
|
| 29 |
+
"step": 1000
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.6,
|
| 33 |
+
"eval_loss": 0.7760354280471802,
|
| 34 |
+
"eval_runtime": 219.0168,
|
| 35 |
+
"eval_samples_per_second": 22.829,
|
| 36 |
+
"eval_steps_per_second": 2.854,
|
| 37 |
+
"eval_wer": 0.644847982692352,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.4,
|
| 42 |
+
"learning_rate": 0.00022809599999999998,
|
| 43 |
+
"loss": 0.6418,
|
| 44 |
+
"step": 1500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 2.4,
|
| 48 |
+
"eval_loss": 0.760543942451477,
|
| 49 |
+
"eval_runtime": 217.3821,
|
| 50 |
+
"eval_samples_per_second": 23.001,
|
| 51 |
+
"eval_steps_per_second": 2.875,
|
| 52 |
+
"eval_wer": 0.6193928513889848,
|
| 53 |
+
"step": 1500
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 3.2,
|
| 57 |
+
"learning_rate": 0.000204096,
|
| 58 |
+
"loss": 0.5028,
|
| 59 |
+
"step": 2000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 3.2,
|
| 63 |
+
"eval_loss": 0.6515631675720215,
|
| 64 |
+
"eval_runtime": 217.5138,
|
| 65 |
+
"eval_samples_per_second": 22.987,
|
| 66 |
+
"eval_steps_per_second": 2.873,
|
| 67 |
+
"eval_wer": 0.532187161959999,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 4.0,
|
| 72 |
+
"learning_rate": 0.00018009599999999998,
|
| 73 |
+
"loss": 0.4133,
|
| 74 |
+
"step": 2500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 4.0,
|
| 78 |
+
"eval_loss": 0.630308210849762,
|
| 79 |
+
"eval_runtime": 220.9761,
|
| 80 |
+
"eval_samples_per_second": 22.627,
|
| 81 |
+
"eval_steps_per_second": 2.828,
|
| 82 |
+
"eval_wer": 0.5097010287923772,
|
| 83 |
+
"step": 2500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 4.8,
|
| 87 |
+
"learning_rate": 0.000156096,
|
| 88 |
+
"loss": 0.3285,
|
| 89 |
+
"step": 3000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 4.8,
|
| 93 |
+
"eval_loss": 0.6422050595283508,
|
| 94 |
+
"eval_runtime": 216.2337,
|
| 95 |
+
"eval_samples_per_second": 23.123,
|
| 96 |
+
"eval_steps_per_second": 2.89,
|
| 97 |
+
"eval_wer": 0.5062487053787199,
|
| 98 |
+
"step": 3000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 5.6,
|
| 102 |
+
"learning_rate": 0.00013209599999999998,
|
| 103 |
+
"loss": 0.2764,
|
| 104 |
+
"step": 3500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 5.6,
|
| 108 |
+
"eval_loss": 0.5936103463172913,
|
| 109 |
+
"eval_runtime": 221.9715,
|
| 110 |
+
"eval_samples_per_second": 22.525,
|
| 111 |
+
"eval_steps_per_second": 2.816,
|
| 112 |
+
"eval_wer": 0.47476351584616444,
|
| 113 |
+
"step": 3500
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 6.4,
|
| 117 |
+
"learning_rate": 0.00010809599999999998,
|
| 118 |
+
"loss": 0.2361,
|
| 119 |
+
"step": 4000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 6.4,
|
| 123 |
+
"eval_loss": 0.6486021280288696,
|
| 124 |
+
"eval_runtime": 217.2436,
|
| 125 |
+
"eval_samples_per_second": 23.016,
|
| 126 |
+
"eval_steps_per_second": 2.877,
|
| 127 |
+
"eval_wer": 0.4683191788073373,
|
| 128 |
+
"step": 4000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 7.2,
|
| 132 |
+
"learning_rate": 8.4144e-05,
|
| 133 |
+
"loss": 0.2049,
|
| 134 |
+
"step": 4500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 7.2,
|
| 138 |
+
"eval_loss": 0.6320939064025879,
|
| 139 |
+
"eval_runtime": 216.2222,
|
| 140 |
+
"eval_samples_per_second": 23.124,
|
| 141 |
+
"eval_steps_per_second": 2.891,
|
| 142 |
+
"eval_wer": 0.453198002255518,
|
| 143 |
+
"step": 4500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 8.0,
|
| 147 |
+
"learning_rate": 6.014399999999999e-05,
|
| 148 |
+
"loss": 0.176,
|
| 149 |
+
"step": 5000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"eval_loss": 0.6229676604270935,
|
| 154 |
+
"eval_runtime": 217.7281,
|
| 155 |
+
"eval_samples_per_second": 22.964,
|
| 156 |
+
"eval_steps_per_second": 2.871,
|
| 157 |
+
"eval_wer": 0.44822665653985133,
|
| 158 |
+
"step": 5000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 8.8,
|
| 162 |
+
"learning_rate": 3.6191999999999995e-05,
|
| 163 |
+
"loss": 0.1393,
|
| 164 |
+
"step": 5500
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 8.8,
|
| 168 |
+
"eval_loss": 0.6595410108566284,
|
| 169 |
+
"eval_runtime": 217.4753,
|
| 170 |
+
"eval_samples_per_second": 22.991,
|
| 171 |
+
"eval_steps_per_second": 2.874,
|
| 172 |
+
"eval_wer": 0.4402863126884393,
|
| 173 |
+
"step": 5500
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 9.6,
|
| 177 |
+
"learning_rate": 1.2192e-05,
|
| 178 |
+
"loss": 0.1141,
|
| 179 |
+
"step": 6000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 9.6,
|
| 183 |
+
"eval_loss": 0.6552333831787109,
|
| 184 |
+
"eval_runtime": 216.5487,
|
| 185 |
+
"eval_samples_per_second": 23.089,
|
| 186 |
+
"eval_steps_per_second": 2.886,
|
| 187 |
+
"eval_wer": 0.43480862620543625,
|
| 188 |
+
"step": 6000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 10.0,
|
| 192 |
+
"step": 6250,
|
| 193 |
+
"total_flos": 1.0733519285960786e+19,
|
| 194 |
+
"train_loss": 0.5376352182006836,
|
| 195 |
+
"train_runtime": 6902.5833,
|
| 196 |
+
"train_samples_per_second": 14.487,
|
| 197 |
+
"train_steps_per_second": 0.905
|
| 198 |
+
}
|
| 199 |
+
],
|
| 200 |
+
"max_steps": 6250,
|
| 201 |
+
"num_train_epochs": 10,
|
| 202 |
+
"total_flos": 1.0733519285960786e+19,
|
| 203 |
+
"trial_name": null,
|
| 204 |
+
"trial_params": null
|
| 205 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ca2ad775929458a40c80853a160c83c7e110384fc53cfba997ea42b133bea3d
|
| 3 |
+
size 3055
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"!": 1, "\"": 2, "&": 3, "'": 4, "(": 5, ")": 6, ",": 7, "-": 8, ".": 9, "/": 10, ":": 11, ";": 12, "=": 13, "?": 14, "^": 15, "_": 16, "a": 17, "b": 18, "c": 19, "d": 20, "e": 21, "f": 22, "g": 23, "h": 24, "i": 25, "j": 26, "k": 27, "l": 28, "m": 29, "n": 30, "o": 31, "p": 32, "q": 33, "r": 34, "s": 35, "t": 36, "u": 37, "v": 38, "w": 39, "x": 40, "y": 41, "z": 42, "{": 43, "}": 44, "«": 45, "°": 46, "º": 47, "»": 48, "½": 49, "×": 50, "à": 51, "á": 52, "â": 53, "ä": 54, "å": 55, "ç": 56, "è": 57, "é": 58, "ê": 59, "ë": 60, "í": 61, "î": 62, "ï": 63, "ñ": 64, "ó": 65, "ô": 66, "ö": 67, "ù": 68, "û": 69, "ü": 70, "ÿ": 71, "ă": 72, "ć": 73, "č": 74, "ę": 75, "ı": 76, "ł": 77, "ń": 78, "ō": 79, "ŏ": 80, "œ": 81, "ř": 82, "ś": 83, "š": 84, "ź": 85, "ž": 86, "̀": 87, "́": 88, "̂": 89, "–": 90, "—": 91, "’": 92, "…": 93, "ℤ": 94, "ℵ": 95, "|": 0, "[UNK]": 96, "[PAD]": 97}
|