Initial model
Browse files- README.md +99 -3
- added_tokens.json +1 -0
- config.json +108 -0
- preprocessor_config.json +10 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +656 -0
- vocab.json +1 -0
README.md
CHANGED
|
@@ -1,3 +1,99 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: wav2vec2-xls-r-300m-west-slavic-cv8
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# wav2vec2-xls-r-300m-west-slavic-cv8
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 2.3462
|
| 18 |
+
- Wer: 0.8556
|
| 19 |
+
- Cer: 0.2799
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0003
|
| 39 |
+
- train_batch_size: 32
|
| 40 |
+
- eval_batch_size: 16
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- lr_scheduler_warmup_steps: 500
|
| 45 |
+
- num_epochs: 50
|
| 46 |
+
- mixed_precision_training: Native AMP
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 51 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|
|
| 52 |
+
| 6.548 | 1.23 | 400 | 3.4763 | 1.0 | 1.0 |
|
| 53 |
+
| 3.42 | 2.45 | 800 | 3.3156 | 1.0 | 1.0 |
|
| 54 |
+
| 3.291 | 3.68 | 1200 | 3.2396 | 1.0 | 1.0 |
|
| 55 |
+
| 2.6515 | 4.91 | 1600 | 2.0422 | 0.9997 | 0.5835 |
|
| 56 |
+
| 1.7019 | 6.13 | 2000 | 1.6337 | 0.9893 | 0.4797 |
|
| 57 |
+
| 1.3604 | 7.36 | 2400 | 1.5221 | 0.9875 | 0.4463 |
|
| 58 |
+
| 1.1965 | 8.59 | 2800 | 1.5284 | 0.9766 | 0.4247 |
|
| 59 |
+
| 1.069 | 9.82 | 3200 | 1.5228 | 0.9672 | 0.4124 |
|
| 60 |
+
| 0.9536 | 11.04 | 3600 | 1.4059 | 0.9600 | 0.3868 |
|
| 61 |
+
| 0.8487 | 12.27 | 4000 | 1.4083 | 0.9501 | 0.3739 |
|
| 62 |
+
| 0.7655 | 13.5 | 4400 | 1.4079 | 0.9369 | 0.3612 |
|
| 63 |
+
| 0.6956 | 14.72 | 4800 | 1.4170 | 0.9411 | 0.3459 |
|
| 64 |
+
| 0.6287 | 15.95 | 5200 | 1.4000 | 0.9235 | 0.3384 |
|
| 65 |
+
| 0.561 | 17.18 | 5600 | 1.4735 | 0.9023 | 0.3295 |
|
| 66 |
+
| 0.5155 | 18.4 | 6000 | 1.5386 | 0.9202 | 0.3223 |
|
| 67 |
+
| 0.4864 | 19.63 | 6400 | 1.6186 | 0.9073 | 0.3259 |
|
| 68 |
+
| 0.4261 | 20.86 | 6800 | 1.6417 | 0.9217 | 0.3130 |
|
| 69 |
+
| 0.4051 | 22.09 | 7200 | 1.6295 | 0.8954 | 0.3026 |
|
| 70 |
+
| 0.3779 | 23.31 | 7600 | 1.8218 | 0.8979 | 0.3153 |
|
| 71 |
+
| 0.35 | 24.54 | 8000 | 1.7790 | 0.8921 | 0.3036 |
|
| 72 |
+
| 0.3343 | 25.77 | 8400 | 1.8588 | 0.9114 | 0.3072 |
|
| 73 |
+
| 0.3137 | 26.99 | 8800 | 1.8096 | 0.8756 | 0.2935 |
|
| 74 |
+
| 0.299 | 28.22 | 9200 | 1.9721 | 0.8863 | 0.3023 |
|
| 75 |
+
| 0.2894 | 29.45 | 9600 | 1.9907 | 0.8872 | 0.2958 |
|
| 76 |
+
| 0.2784 | 30.67 | 10000 | 1.9494 | 0.9090 | 0.2945 |
|
| 77 |
+
| 0.2662 | 31.9 | 10400 | 1.9952 | 0.8978 | 0.2935 |
|
| 78 |
+
| 0.2614 | 33.13 | 10800 | 2.0600 | 0.8949 | 0.2979 |
|
| 79 |
+
| 0.2401 | 34.36 | 11200 | 2.1180 | 0.8914 | 0.2950 |
|
| 80 |
+
| 0.2392 | 35.58 | 11600 | 2.1197 | 0.8713 | 0.2895 |
|
| 81 |
+
| 0.23 | 36.81 | 12000 | 2.1680 | 0.8713 | 0.2941 |
|
| 82 |
+
| 0.2246 | 38.04 | 12400 | 2.1526 | 0.8741 | 0.2879 |
|
| 83 |
+
| 0.2152 | 39.26 | 12800 | 2.2631 | 0.8790 | 0.2889 |
|
| 84 |
+
| 0.212 | 40.49 | 13200 | 2.2724 | 0.8661 | 0.2843 |
|
| 85 |
+
| 0.2044 | 41.72 | 13600 | 2.2438 | 0.8691 | 0.2878 |
|
| 86 |
+
| 0.2029 | 42.94 | 14000 | 2.2519 | 0.8577 | 0.2833 |
|
| 87 |
+
| 0.1972 | 44.17 | 14400 | 2.2697 | 0.8604 | 0.2813 |
|
| 88 |
+
| 0.1884 | 45.4 | 14800 | 2.3294 | 0.8662 | 0.2847 |
|
| 89 |
+
| 0.1877 | 46.63 | 15200 | 2.3077 | 0.8561 | 0.2793 |
|
| 90 |
+
| 0.1871 | 47.85 | 15600 | 2.3518 | 0.8563 | 0.2801 |
|
| 91 |
+
| 0.1838 | 49.08 | 16000 | 2.3462 | 0.8556 | 0.2799 |
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
### Framework versions
|
| 95 |
+
|
| 96 |
+
- Transformers 4.16.0.dev0
|
| 97 |
+
- Pytorch 1.10.1+cu102
|
| 98 |
+
- Datasets 1.18.3
|
| 99 |
+
- Tokenizers 0.11.0
|
added_tokens.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"<s>": 55, "</s>": 56}
|
config.json
ADDED
|
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 0.1,
|
| 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 |
+
"gradient_checkpointing": false,
|
| 56 |
+
"hidden_act": "gelu",
|
| 57 |
+
"hidden_dropout": 0.1,
|
| 58 |
+
"hidden_size": 1024,
|
| 59 |
+
"initializer_range": 0.02,
|
| 60 |
+
"intermediate_size": 4096,
|
| 61 |
+
"layer_norm_eps": 1e-05,
|
| 62 |
+
"layerdrop": 0.1,
|
| 63 |
+
"mask_feature_length": 10,
|
| 64 |
+
"mask_feature_min_masks": 0,
|
| 65 |
+
"mask_feature_prob": 0.0,
|
| 66 |
+
"mask_time_length": 10,
|
| 67 |
+
"mask_time_min_masks": 2,
|
| 68 |
+
"mask_time_prob": 0.05,
|
| 69 |
+
"model_type": "wav2vec2",
|
| 70 |
+
"num_adapter_layers": 3,
|
| 71 |
+
"num_attention_heads": 16,
|
| 72 |
+
"num_codevector_groups": 2,
|
| 73 |
+
"num_codevectors_per_group": 320,
|
| 74 |
+
"num_conv_pos_embedding_groups": 16,
|
| 75 |
+
"num_conv_pos_embeddings": 128,
|
| 76 |
+
"num_feat_extract_layers": 7,
|
| 77 |
+
"num_hidden_layers": 24,
|
| 78 |
+
"num_negatives": 100,
|
| 79 |
+
"output_hidden_size": 1024,
|
| 80 |
+
"pad_token_id": 54,
|
| 81 |
+
"proj_codevector_dim": 768,
|
| 82 |
+
"tdnn_dilation": [
|
| 83 |
+
1,
|
| 84 |
+
2,
|
| 85 |
+
3,
|
| 86 |
+
1,
|
| 87 |
+
1
|
| 88 |
+
],
|
| 89 |
+
"tdnn_dim": [
|
| 90 |
+
512,
|
| 91 |
+
512,
|
| 92 |
+
512,
|
| 93 |
+
512,
|
| 94 |
+
1500
|
| 95 |
+
],
|
| 96 |
+
"tdnn_kernel": [
|
| 97 |
+
5,
|
| 98 |
+
3,
|
| 99 |
+
3,
|
| 100 |
+
1,
|
| 101 |
+
1
|
| 102 |
+
],
|
| 103 |
+
"torch_dtype": "float32",
|
| 104 |
+
"transformers_version": "4.16.0.dev0",
|
| 105 |
+
"use_weighted_layer_sum": false,
|
| 106 |
+
"vocab_size": 57,
|
| 107 |
+
"xvector_output_dim": 512
|
| 108 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0.0,
|
| 7 |
+
"processor_class": "Wav2Vec2Processor",
|
| 8 |
+
"return_attention_mask": true,
|
| 9 |
+
"sampling_rate": 16000
|
| 10 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c6846c706f81b178e7a856cc5831baf4feb947ba1a60f83d8d2289e840883c0
|
| 3 |
+
size 1262157361
|
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": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2Processor"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,656 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 49.079754601226995,
|
| 5 |
+
"global_step": 16000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.23,
|
| 12 |
+
"learning_rate": 0.0002376,
|
| 13 |
+
"loss": 6.548,
|
| 14 |
+
"step": 400
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.23,
|
| 18 |
+
"eval_cer": 1.0,
|
| 19 |
+
"eval_loss": 3.476283073425293,
|
| 20 |
+
"eval_runtime": 60.3486,
|
| 21 |
+
"eval_samples_per_second": 26.513,
|
| 22 |
+
"eval_steps_per_second": 1.657,
|
| 23 |
+
"eval_wer": 1.0,
|
| 24 |
+
"step": 400
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.45,
|
| 28 |
+
"learning_rate": 0.000294379746835443,
|
| 29 |
+
"loss": 3.42,
|
| 30 |
+
"step": 800
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.45,
|
| 34 |
+
"eval_cer": 1.0,
|
| 35 |
+
"eval_loss": 3.3155558109283447,
|
| 36 |
+
"eval_runtime": 60.3859,
|
| 37 |
+
"eval_samples_per_second": 26.496,
|
| 38 |
+
"eval_steps_per_second": 1.656,
|
| 39 |
+
"eval_wer": 1.0,
|
| 40 |
+
"step": 800
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 3.68,
|
| 44 |
+
"learning_rate": 0.00028678481012658224,
|
| 45 |
+
"loss": 3.291,
|
| 46 |
+
"step": 1200
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 3.68,
|
| 50 |
+
"eval_cer": 1.0,
|
| 51 |
+
"eval_loss": 3.2396233081817627,
|
| 52 |
+
"eval_runtime": 60.8505,
|
| 53 |
+
"eval_samples_per_second": 26.294,
|
| 54 |
+
"eval_steps_per_second": 1.643,
|
| 55 |
+
"eval_wer": 1.0,
|
| 56 |
+
"step": 1200
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.91,
|
| 60 |
+
"learning_rate": 0.0002791898734177215,
|
| 61 |
+
"loss": 2.6515,
|
| 62 |
+
"step": 1600
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.91,
|
| 66 |
+
"eval_cer": 0.5835108495504928,
|
| 67 |
+
"eval_loss": 2.042246103286743,
|
| 68 |
+
"eval_runtime": 60.4335,
|
| 69 |
+
"eval_samples_per_second": 26.475,
|
| 70 |
+
"eval_steps_per_second": 1.655,
|
| 71 |
+
"eval_wer": 0.999671772428884,
|
| 72 |
+
"step": 1600
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 6.13,
|
| 76 |
+
"learning_rate": 0.00027159493670886076,
|
| 77 |
+
"loss": 1.7019,
|
| 78 |
+
"step": 2000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 6.13,
|
| 82 |
+
"eval_cer": 0.4797450987471567,
|
| 83 |
+
"eval_loss": 1.6337121725082397,
|
| 84 |
+
"eval_runtime": 60.2878,
|
| 85 |
+
"eval_samples_per_second": 26.539,
|
| 86 |
+
"eval_steps_per_second": 1.659,
|
| 87 |
+
"eval_wer": 0.9892778993435448,
|
| 88 |
+
"step": 2000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 7.36,
|
| 92 |
+
"learning_rate": 0.00026399999999999997,
|
| 93 |
+
"loss": 1.3604,
|
| 94 |
+
"step": 2400
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 7.36,
|
| 98 |
+
"eval_cer": 0.44627576993898255,
|
| 99 |
+
"eval_loss": 1.5220645666122437,
|
| 100 |
+
"eval_runtime": 60.8256,
|
| 101 |
+
"eval_samples_per_second": 26.305,
|
| 102 |
+
"eval_steps_per_second": 1.644,
|
| 103 |
+
"eval_wer": 0.987527352297593,
|
| 104 |
+
"step": 2400
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 8.59,
|
| 108 |
+
"learning_rate": 0.0002564050632911392,
|
| 109 |
+
"loss": 1.1965,
|
| 110 |
+
"step": 2800
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 8.59,
|
| 114 |
+
"eval_cer": 0.4246669314366177,
|
| 115 |
+
"eval_loss": 1.528436303138733,
|
| 116 |
+
"eval_runtime": 60.5379,
|
| 117 |
+
"eval_samples_per_second": 26.43,
|
| 118 |
+
"eval_steps_per_second": 1.652,
|
| 119 |
+
"eval_wer": 0.9765864332603938,
|
| 120 |
+
"step": 2800
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 9.82,
|
| 124 |
+
"learning_rate": 0.00024881012658227843,
|
| 125 |
+
"loss": 1.069,
|
| 126 |
+
"step": 3200
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 9.82,
|
| 130 |
+
"eval_cer": 0.41239123370762176,
|
| 131 |
+
"eval_loss": 1.5227978229522705,
|
| 132 |
+
"eval_runtime": 60.2014,
|
| 133 |
+
"eval_samples_per_second": 26.577,
|
| 134 |
+
"eval_steps_per_second": 1.661,
|
| 135 |
+
"eval_wer": 0.9671772428884027,
|
| 136 |
+
"step": 3200
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 11.04,
|
| 140 |
+
"learning_rate": 0.00024121518987341772,
|
| 141 |
+
"loss": 0.9536,
|
| 142 |
+
"step": 3600
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 11.04,
|
| 146 |
+
"eval_cer": 0.38684695093331406,
|
| 147 |
+
"eval_loss": 1.4059038162231445,
|
| 148 |
+
"eval_runtime": 60.2947,
|
| 149 |
+
"eval_samples_per_second": 26.536,
|
| 150 |
+
"eval_steps_per_second": 1.659,
|
| 151 |
+
"eval_wer": 0.9599562363238512,
|
| 152 |
+
"step": 3600
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 12.27,
|
| 156 |
+
"learning_rate": 0.00023362025316455695,
|
| 157 |
+
"loss": 0.8487,
|
| 158 |
+
"step": 4000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 12.27,
|
| 162 |
+
"eval_cer": 0.37390331082788747,
|
| 163 |
+
"eval_loss": 1.4082870483398438,
|
| 164 |
+
"eval_runtime": 60.1938,
|
| 165 |
+
"eval_samples_per_second": 26.581,
|
| 166 |
+
"eval_steps_per_second": 1.661,
|
| 167 |
+
"eval_wer": 0.950109409190372,
|
| 168 |
+
"step": 4000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 13.5,
|
| 172 |
+
"learning_rate": 0.00022602531645569618,
|
| 173 |
+
"loss": 0.7655,
|
| 174 |
+
"step": 4400
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 13.5,
|
| 178 |
+
"eval_cer": 0.36121240567570495,
|
| 179 |
+
"eval_loss": 1.40787935256958,
|
| 180 |
+
"eval_runtime": 60.2423,
|
| 181 |
+
"eval_samples_per_second": 26.559,
|
| 182 |
+
"eval_steps_per_second": 1.66,
|
| 183 |
+
"eval_wer": 0.9368708971553611,
|
| 184 |
+
"step": 4400
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 14.72,
|
| 188 |
+
"learning_rate": 0.0002184303797468354,
|
| 189 |
+
"loss": 0.6956,
|
| 190 |
+
"step": 4800
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 14.72,
|
| 194 |
+
"eval_cer": 0.34590388850778064,
|
| 195 |
+
"eval_loss": 1.417035698890686,
|
| 196 |
+
"eval_runtime": 60.1538,
|
| 197 |
+
"eval_samples_per_second": 26.598,
|
| 198 |
+
"eval_steps_per_second": 1.662,
|
| 199 |
+
"eval_wer": 0.9411378555798687,
|
| 200 |
+
"step": 4800
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 15.95,
|
| 204 |
+
"learning_rate": 0.00021083544303797464,
|
| 205 |
+
"loss": 0.6287,
|
| 206 |
+
"step": 5200
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 15.95,
|
| 210 |
+
"eval_cer": 0.3383579449037802,
|
| 211 |
+
"eval_loss": 1.3999766111373901,
|
| 212 |
+
"eval_runtime": 60.2038,
|
| 213 |
+
"eval_samples_per_second": 26.576,
|
| 214 |
+
"eval_steps_per_second": 1.661,
|
| 215 |
+
"eval_wer": 0.9235229759299781,
|
| 216 |
+
"step": 5200
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 17.18,
|
| 220 |
+
"learning_rate": 0.00020324050632911393,
|
| 221 |
+
"loss": 0.561,
|
| 222 |
+
"step": 5600
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 17.18,
|
| 226 |
+
"eval_cer": 0.32953027403689933,
|
| 227 |
+
"eval_loss": 1.4734982252120972,
|
| 228 |
+
"eval_runtime": 60.3387,
|
| 229 |
+
"eval_samples_per_second": 26.517,
|
| 230 |
+
"eval_steps_per_second": 1.657,
|
| 231 |
+
"eval_wer": 0.9022975929978119,
|
| 232 |
+
"step": 5600
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 18.4,
|
| 236 |
+
"learning_rate": 0.00019564556962025316,
|
| 237 |
+
"loss": 0.5155,
|
| 238 |
+
"step": 6000
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 18.4,
|
| 242 |
+
"eval_cer": 0.32232732786944435,
|
| 243 |
+
"eval_loss": 1.538634181022644,
|
| 244 |
+
"eval_runtime": 69.1066,
|
| 245 |
+
"eval_samples_per_second": 23.153,
|
| 246 |
+
"eval_steps_per_second": 1.447,
|
| 247 |
+
"eval_wer": 0.9202407002188184,
|
| 248 |
+
"step": 6000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 19.63,
|
| 252 |
+
"learning_rate": 0.0001880506329113924,
|
| 253 |
+
"loss": 0.4864,
|
| 254 |
+
"step": 6400
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 19.63,
|
| 258 |
+
"eval_cer": 0.32590172220818137,
|
| 259 |
+
"eval_loss": 1.618619680404663,
|
| 260 |
+
"eval_runtime": 69.0557,
|
| 261 |
+
"eval_samples_per_second": 23.17,
|
| 262 |
+
"eval_steps_per_second": 1.448,
|
| 263 |
+
"eval_wer": 0.9073304157549235,
|
| 264 |
+
"step": 6400
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 20.86,
|
| 268 |
+
"learning_rate": 0.00018045569620253163,
|
| 269 |
+
"loss": 0.4261,
|
| 270 |
+
"step": 6800
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 20.86,
|
| 274 |
+
"eval_cer": 0.313030292089396,
|
| 275 |
+
"eval_loss": 1.6417021751403809,
|
| 276 |
+
"eval_runtime": 68.875,
|
| 277 |
+
"eval_samples_per_second": 23.23,
|
| 278 |
+
"eval_steps_per_second": 1.452,
|
| 279 |
+
"eval_wer": 0.9216630196936543,
|
| 280 |
+
"step": 6800
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 22.09,
|
| 284 |
+
"learning_rate": 0.00017286075949367088,
|
| 285 |
+
"loss": 0.4051,
|
| 286 |
+
"step": 7200
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 22.09,
|
| 290 |
+
"eval_cer": 0.30263205401307003,
|
| 291 |
+
"eval_loss": 1.6295086145401,
|
| 292 |
+
"eval_runtime": 69.3362,
|
| 293 |
+
"eval_samples_per_second": 23.076,
|
| 294 |
+
"eval_steps_per_second": 1.442,
|
| 295 |
+
"eval_wer": 0.8954048140043763,
|
| 296 |
+
"step": 7200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 23.31,
|
| 300 |
+
"learning_rate": 0.00016526582278481012,
|
| 301 |
+
"loss": 0.3779,
|
| 302 |
+
"step": 7600
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 23.31,
|
| 306 |
+
"eval_cer": 0.31534101166191286,
|
| 307 |
+
"eval_loss": 1.8218317031860352,
|
| 308 |
+
"eval_runtime": 68.8091,
|
| 309 |
+
"eval_samples_per_second": 23.253,
|
| 310 |
+
"eval_steps_per_second": 1.453,
|
| 311 |
+
"eval_wer": 0.8979212253829322,
|
| 312 |
+
"step": 7600
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 24.54,
|
| 316 |
+
"learning_rate": 0.00015767088607594935,
|
| 317 |
+
"loss": 0.35,
|
| 318 |
+
"step": 8000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 24.54,
|
| 322 |
+
"eval_cer": 0.303570783839405,
|
| 323 |
+
"eval_loss": 1.779032588005066,
|
| 324 |
+
"eval_runtime": 68.3457,
|
| 325 |
+
"eval_samples_per_second": 23.41,
|
| 326 |
+
"eval_steps_per_second": 1.463,
|
| 327 |
+
"eval_wer": 0.8921225382932166,
|
| 328 |
+
"step": 8000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 25.77,
|
| 332 |
+
"learning_rate": 0.00015007594936708858,
|
| 333 |
+
"loss": 0.3343,
|
| 334 |
+
"step": 8400
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 25.77,
|
| 338 |
+
"eval_cer": 0.3071812831714626,
|
| 339 |
+
"eval_loss": 1.8588141202926636,
|
| 340 |
+
"eval_runtime": 60.0463,
|
| 341 |
+
"eval_samples_per_second": 26.646,
|
| 342 |
+
"eval_steps_per_second": 1.665,
|
| 343 |
+
"eval_wer": 0.9113785557986871,
|
| 344 |
+
"step": 8400
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 26.99,
|
| 348 |
+
"learning_rate": 0.00014248101265822784,
|
| 349 |
+
"loss": 0.3137,
|
| 350 |
+
"step": 8800
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 26.99,
|
| 354 |
+
"eval_cer": 0.29351554319962453,
|
| 355 |
+
"eval_loss": 1.8095606565475464,
|
| 356 |
+
"eval_runtime": 59.7272,
|
| 357 |
+
"eval_samples_per_second": 26.788,
|
| 358 |
+
"eval_steps_per_second": 1.674,
|
| 359 |
+
"eval_wer": 0.8756017505470459,
|
| 360 |
+
"step": 8800
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 28.22,
|
| 364 |
+
"learning_rate": 0.00013488607594936707,
|
| 365 |
+
"loss": 0.299,
|
| 366 |
+
"step": 9200
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 28.22,
|
| 370 |
+
"eval_cer": 0.3023251615698451,
|
| 371 |
+
"eval_loss": 1.9720637798309326,
|
| 372 |
+
"eval_runtime": 60.067,
|
| 373 |
+
"eval_samples_per_second": 26.637,
|
| 374 |
+
"eval_steps_per_second": 1.665,
|
| 375 |
+
"eval_wer": 0.8863238512035011,
|
| 376 |
+
"step": 9200
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 29.45,
|
| 380 |
+
"learning_rate": 0.00012729113924050633,
|
| 381 |
+
"loss": 0.2894,
|
| 382 |
+
"step": 9600
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 29.45,
|
| 386 |
+
"eval_cer": 0.29584431526880167,
|
| 387 |
+
"eval_loss": 1.9907439947128296,
|
| 388 |
+
"eval_runtime": 68.8361,
|
| 389 |
+
"eval_samples_per_second": 23.244,
|
| 390 |
+
"eval_steps_per_second": 1.453,
|
| 391 |
+
"eval_wer": 0.887199124726477,
|
| 392 |
+
"step": 9600
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 30.67,
|
| 396 |
+
"learning_rate": 0.00011969620253164556,
|
| 397 |
+
"loss": 0.2784,
|
| 398 |
+
"step": 10000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 30.67,
|
| 402 |
+
"eval_cer": 0.2944542730259595,
|
| 403 |
+
"eval_loss": 1.9494301080703735,
|
| 404 |
+
"eval_runtime": 68.9865,
|
| 405 |
+
"eval_samples_per_second": 23.193,
|
| 406 |
+
"eval_steps_per_second": 1.45,
|
| 407 |
+
"eval_wer": 0.9089715536105033,
|
| 408 |
+
"step": 10000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 31.9,
|
| 412 |
+
"learning_rate": 0.00011210126582278481,
|
| 413 |
+
"loss": 0.2662,
|
| 414 |
+
"step": 10400
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 31.9,
|
| 418 |
+
"eval_cer": 0.29346138570964364,
|
| 419 |
+
"eval_loss": 1.995172142982483,
|
| 420 |
+
"eval_runtime": 68.9796,
|
| 421 |
+
"eval_samples_per_second": 23.195,
|
| 422 |
+
"eval_steps_per_second": 1.45,
|
| 423 |
+
"eval_wer": 0.8978118161925602,
|
| 424 |
+
"step": 10400
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 33.13,
|
| 428 |
+
"learning_rate": 0.00010450632911392404,
|
| 429 |
+
"loss": 0.2614,
|
| 430 |
+
"step": 10800
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 33.13,
|
| 434 |
+
"eval_cer": 0.29790229988807454,
|
| 435 |
+
"eval_loss": 2.0600392818450928,
|
| 436 |
+
"eval_runtime": 68.6491,
|
| 437 |
+
"eval_samples_per_second": 23.307,
|
| 438 |
+
"eval_steps_per_second": 1.457,
|
| 439 |
+
"eval_wer": 0.8948577680525164,
|
| 440 |
+
"step": 10800
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 34.36,
|
| 444 |
+
"learning_rate": 9.691139240506327e-05,
|
| 445 |
+
"loss": 0.2401,
|
| 446 |
+
"step": 11200
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 34.36,
|
| 450 |
+
"eval_cer": 0.29495974293244753,
|
| 451 |
+
"eval_loss": 2.118035316467285,
|
| 452 |
+
"eval_runtime": 68.8384,
|
| 453 |
+
"eval_samples_per_second": 23.243,
|
| 454 |
+
"eval_steps_per_second": 1.453,
|
| 455 |
+
"eval_wer": 0.8913566739606127,
|
| 456 |
+
"step": 11200
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 35.58,
|
| 460 |
+
"learning_rate": 8.933544303797467e-05,
|
| 461 |
+
"loss": 0.2392,
|
| 462 |
+
"step": 11600
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 35.58,
|
| 466 |
+
"eval_cer": 0.28950788894104057,
|
| 467 |
+
"eval_loss": 2.1196768283843994,
|
| 468 |
+
"eval_runtime": 68.573,
|
| 469 |
+
"eval_samples_per_second": 23.333,
|
| 470 |
+
"eval_steps_per_second": 1.458,
|
| 471 |
+
"eval_wer": 0.8713347921225383,
|
| 472 |
+
"step": 11600
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 36.81,
|
| 476 |
+
"learning_rate": 8.175949367088606e-05,
|
| 477 |
+
"loss": 0.23,
|
| 478 |
+
"step": 12000
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 36.81,
|
| 482 |
+
"eval_cer": 0.2940932230927537,
|
| 483 |
+
"eval_loss": 2.168043851852417,
|
| 484 |
+
"eval_runtime": 68.6136,
|
| 485 |
+
"eval_samples_per_second": 23.319,
|
| 486 |
+
"eval_steps_per_second": 1.457,
|
| 487 |
+
"eval_wer": 0.8713347921225383,
|
| 488 |
+
"step": 12000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 38.04,
|
| 492 |
+
"learning_rate": 7.416455696202532e-05,
|
| 493 |
+
"loss": 0.2246,
|
| 494 |
+
"step": 12400
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 38.04,
|
| 498 |
+
"eval_cer": 0.2879192692349352,
|
| 499 |
+
"eval_loss": 2.1525843143463135,
|
| 500 |
+
"eval_runtime": 59.7644,
|
| 501 |
+
"eval_samples_per_second": 26.772,
|
| 502 |
+
"eval_steps_per_second": 1.673,
|
| 503 |
+
"eval_wer": 0.874070021881838,
|
| 504 |
+
"step": 12400
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 39.26,
|
| 508 |
+
"learning_rate": 6.656962025316455e-05,
|
| 509 |
+
"loss": 0.2152,
|
| 510 |
+
"step": 12800
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 39.26,
|
| 514 |
+
"eval_cer": 0.28893020904791133,
|
| 515 |
+
"eval_loss": 2.263143301010132,
|
| 516 |
+
"eval_runtime": 60.4724,
|
| 517 |
+
"eval_samples_per_second": 26.458,
|
| 518 |
+
"eval_steps_per_second": 1.654,
|
| 519 |
+
"eval_wer": 0.8789934354485777,
|
| 520 |
+
"step": 12800
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 40.49,
|
| 524 |
+
"learning_rate": 5.897468354430379e-05,
|
| 525 |
+
"loss": 0.212,
|
| 526 |
+
"step": 13200
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 40.49,
|
| 530 |
+
"eval_cer": 0.28430876990287757,
|
| 531 |
+
"eval_loss": 2.2723913192749023,
|
| 532 |
+
"eval_runtime": 60.2908,
|
| 533 |
+
"eval_samples_per_second": 26.538,
|
| 534 |
+
"eval_steps_per_second": 1.659,
|
| 535 |
+
"eval_wer": 0.8660831509846827,
|
| 536 |
+
"step": 13200
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 41.72,
|
| 540 |
+
"learning_rate": 5.1379746835443034e-05,
|
| 541 |
+
"loss": 0.2044,
|
| 542 |
+
"step": 13600
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 41.72,
|
| 546 |
+
"eval_cer": 0.2877929017583132,
|
| 547 |
+
"eval_loss": 2.2438297271728516,
|
| 548 |
+
"eval_runtime": 70.0914,
|
| 549 |
+
"eval_samples_per_second": 22.827,
|
| 550 |
+
"eval_steps_per_second": 1.427,
|
| 551 |
+
"eval_wer": 0.8691466083150985,
|
| 552 |
+
"step": 13600
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 42.94,
|
| 556 |
+
"learning_rate": 4.380379746835442e-05,
|
| 557 |
+
"loss": 0.2029,
|
| 558 |
+
"step": 14000
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 42.94,
|
| 562 |
+
"eval_cer": 0.28327977759324113,
|
| 563 |
+
"eval_loss": 2.2518999576568604,
|
| 564 |
+
"eval_runtime": 69.2505,
|
| 565 |
+
"eval_samples_per_second": 23.105,
|
| 566 |
+
"eval_steps_per_second": 1.444,
|
| 567 |
+
"eval_wer": 0.8576586433260394,
|
| 568 |
+
"step": 14000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 44.17,
|
| 572 |
+
"learning_rate": 3.6208860759493666e-05,
|
| 573 |
+
"loss": 0.1972,
|
| 574 |
+
"step": 14400
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 44.17,
|
| 578 |
+
"eval_cer": 0.28133010795393004,
|
| 579 |
+
"eval_loss": 2.2697150707244873,
|
| 580 |
+
"eval_runtime": 68.5533,
|
| 581 |
+
"eval_samples_per_second": 23.34,
|
| 582 |
+
"eval_steps_per_second": 1.459,
|
| 583 |
+
"eval_wer": 0.8603938730853392,
|
| 584 |
+
"step": 14400
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 45.4,
|
| 588 |
+
"learning_rate": 2.861392405063291e-05,
|
| 589 |
+
"loss": 0.1884,
|
| 590 |
+
"step": 14800
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 45.4,
|
| 594 |
+
"eval_cer": 0.2846878723327436,
|
| 595 |
+
"eval_loss": 2.3294308185577393,
|
| 596 |
+
"eval_runtime": 60.5028,
|
| 597 |
+
"eval_samples_per_second": 26.445,
|
| 598 |
+
"eval_steps_per_second": 1.653,
|
| 599 |
+
"eval_wer": 0.8661925601750547,
|
| 600 |
+
"step": 14800
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 46.63,
|
| 604 |
+
"learning_rate": 2.101898734177215e-05,
|
| 605 |
+
"loss": 0.1877,
|
| 606 |
+
"step": 15200
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 46.63,
|
| 610 |
+
"eval_cer": 0.2792721233346572,
|
| 611 |
+
"eval_loss": 2.3077094554901123,
|
| 612 |
+
"eval_runtime": 60.8923,
|
| 613 |
+
"eval_samples_per_second": 26.276,
|
| 614 |
+
"eval_steps_per_second": 1.642,
|
| 615 |
+
"eval_wer": 0.8561269146608315,
|
| 616 |
+
"step": 15200
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 47.85,
|
| 620 |
+
"learning_rate": 1.3424050632911391e-05,
|
| 621 |
+
"loss": 0.1871,
|
| 622 |
+
"step": 15600
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 47.85,
|
| 626 |
+
"eval_cer": 0.2801025381810304,
|
| 627 |
+
"eval_loss": 2.351794481277466,
|
| 628 |
+
"eval_runtime": 60.3104,
|
| 629 |
+
"eval_samples_per_second": 26.529,
|
| 630 |
+
"eval_steps_per_second": 1.658,
|
| 631 |
+
"eval_wer": 0.8563457330415755,
|
| 632 |
+
"step": 15600
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 49.08,
|
| 636 |
+
"learning_rate": 5.829113924050632e-06,
|
| 637 |
+
"loss": 0.1838,
|
| 638 |
+
"step": 16000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 49.08,
|
| 642 |
+
"eval_cer": 0.27992201321442756,
|
| 643 |
+
"eval_loss": 2.3462095260620117,
|
| 644 |
+
"eval_runtime": 60.2933,
|
| 645 |
+
"eval_samples_per_second": 26.537,
|
| 646 |
+
"eval_steps_per_second": 1.659,
|
| 647 |
+
"eval_wer": 0.8555798687089715,
|
| 648 |
+
"step": 16000
|
| 649 |
+
}
|
| 650 |
+
],
|
| 651 |
+
"max_steps": 16300,
|
| 652 |
+
"num_train_epochs": 50,
|
| 653 |
+
"total_flos": 6.654066355887293e+19,
|
| 654 |
+
"trial_name": null,
|
| 655 |
+
"trial_params": null
|
| 656 |
+
}
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"a": 1, "b": 2, "c": 3, "d": 4, "e": 5, "f": 6, "g": 7, "h": 8, "i": 9, "j": 10, "k": 11, "l": 12, "m": 13, "n": 14, "o": 15, "p": 16, "q": 17, "r": 18, "s": 19, "t": 20, "u": 21, "v": 22, "w": 23, "x": 24, "y": 25, "z": 26, "á": 27, "ä": 28, "è": 29, "é": 30, "í": 31, "ó": 32, "ô": 33, "ú": 34, "ý": 35, "č": 36, "ď": 37, "ě": 38, "ĺ": 39, "ľ": 40, "ł": 41, "ń": 42, "ň": 43, "ŕ": 44, "ř": 45, "ś": 46, "š": 47, "ť": 48, "ů": 49, "ź": 50, "ż": 51, "ž": 52, "|": 0, "[UNK]": 53, "[PAD]": 54}
|