manifoldix
commited on
Commit
•
ad9957b
1
Parent(s):
306a9bf
acoustic model and LM
Browse files- added_tokens.json +1 -0
- alphabet.json +1 -0
- config.json +108 -0
- language_model/5gram.bin +3 -0
- language_model/attrs.json +1 -0
- language_model/unigrams.txt +0 -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 +916 -0
- training_args.bin +3 -0
- vocab.json +1 -0
added_tokens.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"<s>": 38, "</s>": 39}
|
alphabet.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"labels": [" ", "\u0622", "\u0626", "\u0627", "\u0628", "\u062a", "\u062b", "\u062c", "\u062d", "\u062e", "\u062f", "\u0630", "\u0631", "\u0632", "\u0633", "\u0634", "\u0635", "\u0636", "\u0637", "\u0638", "\u0639", "\u063a", "\u0641", "\u0642", "\u0644", "\u0645", "\u0646", "\u0647", "\u0648", "\u067e", "\u0686", "\u0698", "\u06a9", "\u06af", "\u06cc", "\u200c", "\u2047", "", "<s>", "</s>"], "is_bpe": false}
|
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": 0.0,
|
| 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 |
+
"gradient_checkpointing": false,
|
| 56 |
+
"hidden_act": "gelu",
|
| 57 |
+
"hidden_dropout": 0.0,
|
| 58 |
+
"hidden_size": 1024,
|
| 59 |
+
"initializer_range": 0.02,
|
| 60 |
+
"intermediate_size": 4096,
|
| 61 |
+
"layer_norm_eps": 1e-05,
|
| 62 |
+
"layerdrop": 0.0,
|
| 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": 37,
|
| 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": 40,
|
| 107 |
+
"xvector_output_dim": 512
|
| 108 |
+
}
|
language_model/5gram.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2827e996580d285c26c7e1fced3df2aca861a2507c3907f1fdcccbccf54e3291
|
| 3 |
+
size 1062932976
|
language_model/attrs.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}
|
language_model/unigrams.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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": "Wav2Vec2ProcessorWithLM",
|
| 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 sha256:67f553a9f4b259d5f91ab7a99ae359581e926d384978566f6d7afacb4e15ad10
|
| 3 |
+
size 1262087665
|
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": "Wav2Vec2ProcessorWithLM"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,916 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 119.99875156054931,
|
| 5 |
+
"global_step": 24000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 2.0,
|
| 12 |
+
"learning_rate": 7.960000000000001e-05,
|
| 13 |
+
"loss": 7.6701,
|
| 14 |
+
"step": 400
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 2.0,
|
| 18 |
+
"eval_loss": 2.900460958480835,
|
| 19 |
+
"eval_runtime": 252.4053,
|
| 20 |
+
"eval_samples_per_second": 20.653,
|
| 21 |
+
"eval_steps_per_second": 2.583,
|
| 22 |
+
"eval_wer": 1.0,
|
| 23 |
+
"step": 400
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 4.0,
|
| 27 |
+
"learning_rate": 9.873191489361703e-05,
|
| 28 |
+
"loss": 1.0784,
|
| 29 |
+
"step": 800
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 4.0,
|
| 33 |
+
"eval_loss": 0.4933229088783264,
|
| 34 |
+
"eval_runtime": 254.2522,
|
| 35 |
+
"eval_samples_per_second": 20.503,
|
| 36 |
+
"eval_steps_per_second": 2.564,
|
| 37 |
+
"eval_wer": 0.46976841118086854,
|
| 38 |
+
"step": 800
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 6.0,
|
| 42 |
+
"learning_rate": 9.702978723404256e-05,
|
| 43 |
+
"loss": 0.3128,
|
| 44 |
+
"step": 1200
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 6.0,
|
| 48 |
+
"eval_loss": 0.3993886709213257,
|
| 49 |
+
"eval_runtime": 252.398,
|
| 50 |
+
"eval_samples_per_second": 20.654,
|
| 51 |
+
"eval_steps_per_second": 2.583,
|
| 52 |
+
"eval_wer": 0.37059421158204603,
|
| 53 |
+
"step": 1200
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 8.0,
|
| 57 |
+
"learning_rate": 9.532765957446809e-05,
|
| 58 |
+
"loss": 0.2158,
|
| 59 |
+
"step": 1600
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 8.0,
|
| 63 |
+
"eval_loss": 0.3813767731189728,
|
| 64 |
+
"eval_runtime": 260.377,
|
| 65 |
+
"eval_samples_per_second": 20.021,
|
| 66 |
+
"eval_steps_per_second": 2.504,
|
| 67 |
+
"eval_wer": 0.3755438038919426,
|
| 68 |
+
"step": 1600
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 10.0,
|
| 72 |
+
"learning_rate": 9.362553191489361e-05,
|
| 73 |
+
"loss": 0.1716,
|
| 74 |
+
"step": 2000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 10.0,
|
| 78 |
+
"eval_loss": 0.3713369071483612,
|
| 79 |
+
"eval_runtime": 256.1576,
|
| 80 |
+
"eval_samples_per_second": 20.351,
|
| 81 |
+
"eval_steps_per_second": 2.545,
|
| 82 |
+
"eval_wer": 0.33745799359158046,
|
| 83 |
+
"step": 2000
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 12.0,
|
| 87 |
+
"learning_rate": 9.192340425531915e-05,
|
| 88 |
+
"loss": 0.1419,
|
| 89 |
+
"step": 2400
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 12.0,
|
| 93 |
+
"eval_loss": 0.3995266556739807,
|
| 94 |
+
"eval_runtime": 252.1996,
|
| 95 |
+
"eval_samples_per_second": 20.67,
|
| 96 |
+
"eval_steps_per_second": 2.585,
|
| 97 |
+
"eval_wer": 0.35183786177612214,
|
| 98 |
+
"step": 2400
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 14.0,
|
| 102 |
+
"learning_rate": 9.022127659574468e-05,
|
| 103 |
+
"loss": 0.1236,
|
| 104 |
+
"step": 2800
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 14.0,
|
| 108 |
+
"eval_loss": 0.41960370540618896,
|
| 109 |
+
"eval_runtime": 256.7174,
|
| 110 |
+
"eval_samples_per_second": 20.306,
|
| 111 |
+
"eval_steps_per_second": 2.54,
|
| 112 |
+
"eval_wer": 0.34042774897751843,
|
| 113 |
+
"step": 2800
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 16.0,
|
| 117 |
+
"learning_rate": 8.851914893617021e-05,
|
| 118 |
+
"loss": 0.1136,
|
| 119 |
+
"step": 3200
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 16.0,
|
| 123 |
+
"eval_loss": 0.3961251676082611,
|
| 124 |
+
"eval_runtime": 257.0042,
|
| 125 |
+
"eval_samples_per_second": 20.284,
|
| 126 |
+
"eval_steps_per_second": 2.537,
|
| 127 |
+
"eval_wer": 0.32029072342199183,
|
| 128 |
+
"step": 3200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 18.0,
|
| 132 |
+
"learning_rate": 8.682127659574468e-05,
|
| 133 |
+
"loss": 0.1018,
|
| 134 |
+
"step": 3600
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 18.0,
|
| 138 |
+
"eval_loss": 0.4284366965293884,
|
| 139 |
+
"eval_runtime": 253.1831,
|
| 140 |
+
"eval_samples_per_second": 20.59,
|
| 141 |
+
"eval_steps_per_second": 2.575,
|
| 142 |
+
"eval_wer": 0.3373798421340558,
|
| 143 |
+
"step": 3600
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 20.0,
|
| 147 |
+
"learning_rate": 8.511914893617021e-05,
|
| 148 |
+
"loss": 0.0948,
|
| 149 |
+
"step": 4000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 20.0,
|
| 153 |
+
"eval_loss": 0.4246082305908203,
|
| 154 |
+
"eval_runtime": 250.1867,
|
| 155 |
+
"eval_samples_per_second": 20.836,
|
| 156 |
+
"eval_steps_per_second": 2.606,
|
| 157 |
+
"eval_wer": 0.32953864589574594,
|
| 158 |
+
"step": 4000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 22.0,
|
| 162 |
+
"learning_rate": 8.341702127659575e-05,
|
| 163 |
+
"loss": 0.0837,
|
| 164 |
+
"step": 4400
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 22.0,
|
| 168 |
+
"eval_loss": 0.41016092896461487,
|
| 169 |
+
"eval_runtime": 255.5501,
|
| 170 |
+
"eval_samples_per_second": 20.399,
|
| 171 |
+
"eval_steps_per_second": 2.551,
|
| 172 |
+
"eval_wer": 0.31726886706437074,
|
| 173 |
+
"step": 4400
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 24.0,
|
| 177 |
+
"learning_rate": 8.171489361702128e-05,
|
| 178 |
+
"loss": 0.0823,
|
| 179 |
+
"step": 4800
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 24.0,
|
| 183 |
+
"eval_loss": 0.42129427194595337,
|
| 184 |
+
"eval_runtime": 254.0415,
|
| 185 |
+
"eval_samples_per_second": 20.52,
|
| 186 |
+
"eval_steps_per_second": 2.567,
|
| 187 |
+
"eval_wer": 0.3245109021283247,
|
| 188 |
+
"step": 4800
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 26.0,
|
| 192 |
+
"learning_rate": 8.001276595744681e-05,
|
| 193 |
+
"loss": 0.079,
|
| 194 |
+
"step": 5200
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 26.0,
|
| 198 |
+
"eval_loss": 0.4289919435977936,
|
| 199 |
+
"eval_runtime": 256.8225,
|
| 200 |
+
"eval_samples_per_second": 20.298,
|
| 201 |
+
"eval_steps_per_second": 2.539,
|
| 202 |
+
"eval_wer": 0.3159923932581343,
|
| 203 |
+
"step": 5200
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 28.0,
|
| 207 |
+
"learning_rate": 7.831063829787234e-05,
|
| 208 |
+
"loss": 0.0736,
|
| 209 |
+
"step": 5600
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 28.0,
|
| 213 |
+
"eval_loss": 0.45376530289649963,
|
| 214 |
+
"eval_runtime": 250.495,
|
| 215 |
+
"eval_samples_per_second": 20.811,
|
| 216 |
+
"eval_steps_per_second": 2.603,
|
| 217 |
+
"eval_wer": 0.3086982572224972,
|
| 218 |
+
"step": 5600
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 30.0,
|
| 222 |
+
"learning_rate": 7.66127659574468e-05,
|
| 223 |
+
"loss": 0.0702,
|
| 224 |
+
"step": 6000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 30.0,
|
| 228 |
+
"eval_loss": 0.4636918306350708,
|
| 229 |
+
"eval_runtime": 251.4184,
|
| 230 |
+
"eval_samples_per_second": 20.734,
|
| 231 |
+
"eval_steps_per_second": 2.593,
|
| 232 |
+
"eval_wer": 0.31151170969338576,
|
| 233 |
+
"step": 6000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 32.0,
|
| 237 |
+
"learning_rate": 7.491063829787235e-05,
|
| 238 |
+
"loss": 0.0668,
|
| 239 |
+
"step": 6400
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 32.0,
|
| 243 |
+
"eval_loss": 0.4827902615070343,
|
| 244 |
+
"eval_runtime": 248.7074,
|
| 245 |
+
"eval_samples_per_second": 20.96,
|
| 246 |
+
"eval_steps_per_second": 2.622,
|
| 247 |
+
"eval_wer": 0.3185192903847657,
|
| 248 |
+
"step": 6400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 34.0,
|
| 252 |
+
"learning_rate": 7.320851063829788e-05,
|
| 253 |
+
"loss": 0.0646,
|
| 254 |
+
"step": 6800
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 34.0,
|
| 258 |
+
"eval_loss": 0.4427362084388733,
|
| 259 |
+
"eval_runtime": 252.8917,
|
| 260 |
+
"eval_samples_per_second": 20.614,
|
| 261 |
+
"eval_steps_per_second": 2.578,
|
| 262 |
+
"eval_wer": 0.311381457264178,
|
| 263 |
+
"step": 6800
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 36.0,
|
| 267 |
+
"learning_rate": 7.15063829787234e-05,
|
| 268 |
+
"loss": 0.06,
|
| 269 |
+
"step": 7200
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 36.0,
|
| 273 |
+
"eval_loss": 0.4571715295314789,
|
| 274 |
+
"eval_runtime": 252.2048,
|
| 275 |
+
"eval_samples_per_second": 20.67,
|
| 276 |
+
"eval_steps_per_second": 2.585,
|
| 277 |
+
"eval_wer": 0.311615911636752,
|
| 278 |
+
"step": 7200
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 38.0,
|
| 282 |
+
"learning_rate": 6.980425531914893e-05,
|
| 283 |
+
"loss": 0.0584,
|
| 284 |
+
"step": 7600
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 38.0,
|
| 288 |
+
"eval_loss": 0.4944392740726471,
|
| 289 |
+
"eval_runtime": 251.4845,
|
| 290 |
+
"eval_samples_per_second": 20.729,
|
| 291 |
+
"eval_steps_per_second": 2.593,
|
| 292 |
+
"eval_wer": 0.30804699507645816,
|
| 293 |
+
"step": 7600
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 40.0,
|
| 297 |
+
"learning_rate": 6.810212765957446e-05,
|
| 298 |
+
"loss": 0.0545,
|
| 299 |
+
"step": 8000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 40.0,
|
| 303 |
+
"eval_loss": 0.4599160850048065,
|
| 304 |
+
"eval_runtime": 253.7962,
|
| 305 |
+
"eval_samples_per_second": 20.54,
|
| 306 |
+
"eval_steps_per_second": 2.569,
|
| 307 |
+
"eval_wer": 0.3099747310287337,
|
| 308 |
+
"step": 8000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 42.0,
|
| 312 |
+
"learning_rate": 6.64e-05,
|
| 313 |
+
"loss": 0.0536,
|
| 314 |
+
"step": 8400
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 42.0,
|
| 318 |
+
"eval_loss": 0.4586937427520752,
|
| 319 |
+
"eval_runtime": 256.4427,
|
| 320 |
+
"eval_samples_per_second": 20.328,
|
| 321 |
+
"eval_steps_per_second": 2.542,
|
| 322 |
+
"eval_wer": 0.30338395811081875,
|
| 323 |
+
"step": 8400
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 44.0,
|
| 327 |
+
"learning_rate": 6.469787234042553e-05,
|
| 328 |
+
"loss": 0.0506,
|
| 329 |
+
"step": 8800
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 44.0,
|
| 333 |
+
"eval_loss": 0.46839669346809387,
|
| 334 |
+
"eval_runtime": 253.5984,
|
| 335 |
+
"eval_samples_per_second": 20.556,
|
| 336 |
+
"eval_steps_per_second": 2.571,
|
| 337 |
+
"eval_wer": 0.3020814338187407,
|
| 338 |
+
"step": 8800
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 46.0,
|
| 342 |
+
"learning_rate": 6.299574468085107e-05,
|
| 343 |
+
"loss": 0.0504,
|
| 344 |
+
"step": 9200
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 46.0,
|
| 348 |
+
"eval_loss": 0.4694036841392517,
|
| 349 |
+
"eval_runtime": 252.7537,
|
| 350 |
+
"eval_samples_per_second": 20.625,
|
| 351 |
+
"eval_steps_per_second": 2.58,
|
| 352 |
+
"eval_wer": 0.30710917758616196,
|
| 353 |
+
"step": 9200
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 48.0,
|
| 357 |
+
"learning_rate": 6.12936170212766e-05,
|
| 358 |
+
"loss": 0.048,
|
| 359 |
+
"step": 9600
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 48.0,
|
| 363 |
+
"eval_loss": 0.4677378535270691,
|
| 364 |
+
"eval_runtime": 252.9941,
|
| 365 |
+
"eval_samples_per_second": 20.605,
|
| 366 |
+
"eval_steps_per_second": 2.577,
|
| 367 |
+
"eval_wer": 0.2971578919946857,
|
| 368 |
+
"step": 9600
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 50.0,
|
| 372 |
+
"learning_rate": 5.9591489361702134e-05,
|
| 373 |
+
"loss": 0.045,
|
| 374 |
+
"step": 10000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 50.0,
|
| 378 |
+
"eval_loss": 0.46043330430984497,
|
| 379 |
+
"eval_runtime": 249.2435,
|
| 380 |
+
"eval_samples_per_second": 20.915,
|
| 381 |
+
"eval_steps_per_second": 2.616,
|
| 382 |
+
"eval_wer": 0.29778310365488314,
|
| 383 |
+
"step": 10000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 52.0,
|
| 387 |
+
"learning_rate": 5.7893617021276604e-05,
|
| 388 |
+
"loss": 0.0436,
|
| 389 |
+
"step": 10400
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 52.0,
|
| 393 |
+
"eval_loss": 0.4766680598258972,
|
| 394 |
+
"eval_runtime": 251.6774,
|
| 395 |
+
"eval_samples_per_second": 20.713,
|
| 396 |
+
"eval_steps_per_second": 2.591,
|
| 397 |
+
"eval_wer": 0.29731419490973504,
|
| 398 |
+
"step": 10400
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 54.0,
|
| 402 |
+
"learning_rate": 5.619148936170213e-05,
|
| 403 |
+
"loss": 0.0422,
|
| 404 |
+
"step": 10800
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 54.0,
|
| 408 |
+
"eval_loss": 0.4668702185153961,
|
| 409 |
+
"eval_runtime": 252.6671,
|
| 410 |
+
"eval_samples_per_second": 20.632,
|
| 411 |
+
"eval_steps_per_second": 2.58,
|
| 412 |
+
"eval_wer": 0.2975486492823091,
|
| 413 |
+
"step": 10800
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 56.0,
|
| 417 |
+
"learning_rate": 5.448936170212766e-05,
|
| 418 |
+
"loss": 0.0404,
|
| 419 |
+
"step": 11200
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 56.0,
|
| 423 |
+
"eval_loss": 0.4487351179122925,
|
| 424 |
+
"eval_runtime": 250.621,
|
| 425 |
+
"eval_samples_per_second": 20.8,
|
| 426 |
+
"eval_steps_per_second": 2.602,
|
| 427 |
+
"eval_wer": 0.2965066298486467,
|
| 428 |
+
"step": 11200
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 58.0,
|
| 432 |
+
"learning_rate": 5.278723404255319e-05,
|
| 433 |
+
"loss": 0.04,
|
| 434 |
+
"step": 11600
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 58.0,
|
| 438 |
+
"eval_loss": 0.49005138874053955,
|
| 439 |
+
"eval_runtime": 254.1559,
|
| 440 |
+
"eval_samples_per_second": 20.511,
|
| 441 |
+
"eval_steps_per_second": 2.565,
|
| 442 |
+
"eval_wer": 0.2988511735743872,
|
| 443 |
+
"step": 11600
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 60.0,
|
| 447 |
+
"learning_rate": 5.108510638297873e-05,
|
| 448 |
+
"loss": 0.0375,
|
| 449 |
+
"step": 12000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 60.0,
|
| 453 |
+
"eval_loss": 0.46530571579933167,
|
| 454 |
+
"eval_runtime": 255.1439,
|
| 455 |
+
"eval_samples_per_second": 20.432,
|
| 456 |
+
"eval_steps_per_second": 2.555,
|
| 457 |
+
"eval_wer": 0.2963763774194389,
|
| 458 |
+
"step": 12000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 62.0,
|
| 462 |
+
"learning_rate": 4.938297872340426e-05,
|
| 463 |
+
"loss": 0.0353,
|
| 464 |
+
"step": 12400
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 62.0,
|
| 468 |
+
"eval_loss": 0.5175049901008606,
|
| 469 |
+
"eval_runtime": 253.9576,
|
| 470 |
+
"eval_samples_per_second": 20.527,
|
| 471 |
+
"eval_steps_per_second": 2.567,
|
| 472 |
+
"eval_wer": 0.2963242764477558,
|
| 473 |
+
"step": 12400
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 64.0,
|
| 477 |
+
"learning_rate": 4.768085106382979e-05,
|
| 478 |
+
"loss": 0.0346,
|
| 479 |
+
"step": 12800
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 64.0,
|
| 483 |
+
"eval_loss": 0.5116600394248962,
|
| 484 |
+
"eval_runtime": 256.8702,
|
| 485 |
+
"eval_samples_per_second": 20.294,
|
| 486 |
+
"eval_steps_per_second": 2.538,
|
| 487 |
+
"eval_wer": 0.2914528355953839,
|
| 488 |
+
"step": 12800
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 66.0,
|
| 492 |
+
"learning_rate": 4.597872340425532e-05,
|
| 493 |
+
"loss": 0.0341,
|
| 494 |
+
"step": 13200
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 66.0,
|
| 498 |
+
"eval_loss": 0.4671209454536438,
|
| 499 |
+
"eval_runtime": 255.8006,
|
| 500 |
+
"eval_samples_per_second": 20.379,
|
| 501 |
+
"eval_steps_per_second": 2.549,
|
| 502 |
+
"eval_wer": 0.2945528434105296,
|
| 503 |
+
"step": 13200
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 68.0,
|
| 507 |
+
"learning_rate": 4.4280851063829785e-05,
|
| 508 |
+
"loss": 0.0332,
|
| 509 |
+
"step": 13600
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 68.0,
|
| 513 |
+
"eval_loss": 0.48402974009513855,
|
| 514 |
+
"eval_runtime": 251.9224,
|
| 515 |
+
"eval_samples_per_second": 20.693,
|
| 516 |
+
"eval_steps_per_second": 2.588,
|
| 517 |
+
"eval_wer": 0.2882746763227134,
|
| 518 |
+
"step": 13600
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 70.0,
|
| 522 |
+
"learning_rate": 4.257872340425532e-05,
|
| 523 |
+
"loss": 0.0307,
|
| 524 |
+
"step": 14000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 70.0,
|
| 528 |
+
"eval_loss": 0.4735446870326996,
|
| 529 |
+
"eval_runtime": 251.6191,
|
| 530 |
+
"eval_samples_per_second": 20.718,
|
| 531 |
+
"eval_steps_per_second": 2.591,
|
| 532 |
+
"eval_wer": 0.2853570219084586,
|
| 533 |
+
"step": 14000
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 72.0,
|
| 537 |
+
"learning_rate": 4.0876595744680854e-05,
|
| 538 |
+
"loss": 0.0296,
|
| 539 |
+
"step": 14400
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 72.0,
|
| 543 |
+
"eval_loss": 0.49666687846183777,
|
| 544 |
+
"eval_runtime": 255.1334,
|
| 545 |
+
"eval_samples_per_second": 20.432,
|
| 546 |
+
"eval_steps_per_second": 2.556,
|
| 547 |
+
"eval_wer": 0.2870242530023185,
|
| 548 |
+
"step": 14400
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 74.0,
|
| 552 |
+
"learning_rate": 3.917446808510639e-05,
|
| 553 |
+
"loss": 0.0288,
|
| 554 |
+
"step": 14800
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 74.0,
|
| 558 |
+
"eval_loss": 0.4831916093826294,
|
| 559 |
+
"eval_runtime": 250.196,
|
| 560 |
+
"eval_samples_per_second": 20.836,
|
| 561 |
+
"eval_steps_per_second": 2.606,
|
| 562 |
+
"eval_wer": 0.28111079271628414,
|
| 563 |
+
"step": 14800
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 76.0,
|
| 567 |
+
"learning_rate": 3.747234042553192e-05,
|
| 568 |
+
"loss": 0.0278,
|
| 569 |
+
"step": 15200
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 76.0,
|
| 573 |
+
"eval_loss": 0.5073911547660828,
|
| 574 |
+
"eval_runtime": 251.6593,
|
| 575 |
+
"eval_samples_per_second": 20.715,
|
| 576 |
+
"eval_steps_per_second": 2.591,
|
| 577 |
+
"eval_wer": 0.2897595540156824,
|
| 578 |
+
"step": 15200
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 78.0,
|
| 582 |
+
"learning_rate": 3.577021276595745e-05,
|
| 583 |
+
"loss": 0.0264,
|
| 584 |
+
"step": 15600
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 78.0,
|
| 588 |
+
"eval_loss": 0.49896690249443054,
|
| 589 |
+
"eval_runtime": 253.2919,
|
| 590 |
+
"eval_samples_per_second": 20.581,
|
| 591 |
+
"eval_steps_per_second": 2.574,
|
| 592 |
+
"eval_wer": 0.28066793445697763,
|
| 593 |
+
"step": 15600
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 80.0,
|
| 597 |
+
"learning_rate": 3.406808510638298e-05,
|
| 598 |
+
"loss": 0.0259,
|
| 599 |
+
"step": 16000
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 80.0,
|
| 603 |
+
"eval_loss": 0.4933984577655792,
|
| 604 |
+
"eval_runtime": 250.843,
|
| 605 |
+
"eval_samples_per_second": 20.782,
|
| 606 |
+
"eval_steps_per_second": 2.599,
|
| 607 |
+
"eval_wer": 0.28478391121994423,
|
| 608 |
+
"step": 16000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 82.0,
|
| 612 |
+
"learning_rate": 3.2365957446808515e-05,
|
| 613 |
+
"loss": 0.0256,
|
| 614 |
+
"step": 16400
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 82.0,
|
| 618 |
+
"eval_loss": 0.5108290314674377,
|
| 619 |
+
"eval_runtime": 254.0809,
|
| 620 |
+
"eval_samples_per_second": 20.517,
|
| 621 |
+
"eval_steps_per_second": 2.566,
|
| 622 |
+
"eval_wer": 0.2834032354703415,
|
| 623 |
+
"step": 16400
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 84.0,
|
| 627 |
+
"learning_rate": 3.066382978723404e-05,
|
| 628 |
+
"loss": 0.0241,
|
| 629 |
+
"step": 16800
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 84.0,
|
| 633 |
+
"eval_loss": 0.5010423064231873,
|
| 634 |
+
"eval_runtime": 253.2137,
|
| 635 |
+
"eval_samples_per_second": 20.587,
|
| 636 |
+
"eval_steps_per_second": 2.575,
|
| 637 |
+
"eval_wer": 0.28137129757469975,
|
| 638 |
+
"step": 16800
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 86.0,
|
| 642 |
+
"learning_rate": 2.8961702127659574e-05,
|
| 643 |
+
"loss": 0.0225,
|
| 644 |
+
"step": 17200
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 86.0,
|
| 648 |
+
"eval_loss": 0.5098214745521545,
|
| 649 |
+
"eval_runtime": 251.7862,
|
| 650 |
+
"eval_samples_per_second": 20.704,
|
| 651 |
+
"eval_steps_per_second": 2.589,
|
| 652 |
+
"eval_wer": 0.2809544898012348,
|
| 653 |
+
"step": 17200
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 88.0,
|
| 657 |
+
"learning_rate": 2.725957446808511e-05,
|
| 658 |
+
"loss": 0.0214,
|
| 659 |
+
"step": 17600
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 88.0,
|
| 663 |
+
"eval_loss": 0.5001631379127502,
|
| 664 |
+
"eval_runtime": 251.7107,
|
| 665 |
+
"eval_samples_per_second": 20.71,
|
| 666 |
+
"eval_steps_per_second": 2.59,
|
| 667 |
+
"eval_wer": 0.27485867611430953,
|
| 668 |
+
"step": 17600
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 90.0,
|
| 672 |
+
"learning_rate": 2.5565957446808516e-05,
|
| 673 |
+
"loss": 0.0212,
|
| 674 |
+
"step": 18000
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 90.0,
|
| 678 |
+
"eval_loss": 0.5039480328559875,
|
| 679 |
+
"eval_runtime": 256.5398,
|
| 680 |
+
"eval_samples_per_second": 20.32,
|
| 681 |
+
"eval_steps_per_second": 2.542,
|
| 682 |
+
"eval_wer": 0.27517128194440826,
|
| 683 |
+
"step": 18000
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 92.0,
|
| 687 |
+
"learning_rate": 2.3863829787234044e-05,
|
| 688 |
+
"loss": 0.0198,
|
| 689 |
+
"step": 18400
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 92.0,
|
| 693 |
+
"eval_loss": 0.5044199824333191,
|
| 694 |
+
"eval_runtime": 250.6127,
|
| 695 |
+
"eval_samples_per_second": 20.801,
|
| 696 |
+
"eval_steps_per_second": 2.602,
|
| 697 |
+
"eval_wer": 0.2775939771276734,
|
| 698 |
+
"step": 18400
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 94.0,
|
| 702 |
+
"learning_rate": 2.2161702127659575e-05,
|
| 703 |
+
"loss": 0.0194,
|
| 704 |
+
"step": 18800
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 94.0,
|
| 708 |
+
"eval_loss": 0.5091202855110168,
|
| 709 |
+
"eval_runtime": 252.5846,
|
| 710 |
+
"eval_samples_per_second": 20.639,
|
| 711 |
+
"eval_steps_per_second": 2.581,
|
| 712 |
+
"eval_wer": 0.2784796936462865,
|
| 713 |
+
"step": 18800
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 96.0,
|
| 717 |
+
"learning_rate": 2.0459574468085106e-05,
|
| 718 |
+
"loss": 0.0193,
|
| 719 |
+
"step": 19200
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 96.0,
|
| 723 |
+
"eval_loss": 0.5078316926956177,
|
| 724 |
+
"eval_runtime": 254.2064,
|
| 725 |
+
"eval_samples_per_second": 20.507,
|
| 726 |
+
"eval_steps_per_second": 2.565,
|
| 727 |
+
"eval_wer": 0.2763435538072785,
|
| 728 |
+
"step": 19200
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 98.0,
|
| 732 |
+
"learning_rate": 1.875744680851064e-05,
|
| 733 |
+
"loss": 0.0189,
|
| 734 |
+
"step": 19600
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 98.0,
|
| 738 |
+
"eval_loss": 0.50649094581604,
|
| 739 |
+
"eval_runtime": 250.3726,
|
| 740 |
+
"eval_samples_per_second": 20.821,
|
| 741 |
+
"eval_steps_per_second": 2.604,
|
| 742 |
+
"eval_wer": 0.2715502644124313,
|
| 743 |
+
"step": 19600
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 100.0,
|
| 747 |
+
"learning_rate": 1.7055319148936173e-05,
|
| 748 |
+
"loss": 0.0169,
|
| 749 |
+
"step": 20000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 100.0,
|
| 753 |
+
"eval_loss": 0.5111807584762573,
|
| 754 |
+
"eval_runtime": 251.2786,
|
| 755 |
+
"eval_samples_per_second": 20.746,
|
| 756 |
+
"eval_steps_per_second": 2.595,
|
| 757 |
+
"eval_wer": 0.2712897595540157,
|
| 758 |
+
"step": 20000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 102.0,
|
| 762 |
+
"learning_rate": 1.5353191489361704e-05,
|
| 763 |
+
"loss": 0.0162,
|
| 764 |
+
"step": 20400
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 102.0,
|
| 768 |
+
"eval_loss": 0.5116817951202393,
|
| 769 |
+
"eval_runtime": 249.9762,
|
| 770 |
+
"eval_samples_per_second": 20.854,
|
| 771 |
+
"eval_steps_per_second": 2.608,
|
| 772 |
+
"eval_wer": 0.27011748769114546,
|
| 773 |
+
"step": 20400
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 104.0,
|
| 777 |
+
"learning_rate": 1.3651063829787234e-05,
|
| 778 |
+
"loss": 0.0155,
|
| 779 |
+
"step": 20800
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 104.0,
|
| 783 |
+
"eval_loss": 0.5181553363800049,
|
| 784 |
+
"eval_runtime": 252.5167,
|
| 785 |
+
"eval_samples_per_second": 20.644,
|
| 786 |
+
"eval_steps_per_second": 2.582,
|
| 787 |
+
"eval_wer": 0.26858050902649333,
|
| 788 |
+
"step": 20800
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 106.0,
|
| 792 |
+
"learning_rate": 1.1948936170212767e-05,
|
| 793 |
+
"loss": 0.0162,
|
| 794 |
+
"step": 21200
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 106.0,
|
| 798 |
+
"eval_loss": 0.5102177262306213,
|
| 799 |
+
"eval_runtime": 253.88,
|
| 800 |
+
"eval_samples_per_second": 20.533,
|
| 801 |
+
"eval_steps_per_second": 2.568,
|
| 802 |
+
"eval_wer": 0.26886706437075053,
|
| 803 |
+
"step": 21200
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 108.0,
|
| 807 |
+
"learning_rate": 1.0246808510638298e-05,
|
| 808 |
+
"loss": 0.015,
|
| 809 |
+
"step": 21600
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 108.0,
|
| 813 |
+
"eval_loss": 0.5183060169219971,
|
| 814 |
+
"eval_runtime": 256.9895,
|
| 815 |
+
"eval_samples_per_second": 20.285,
|
| 816 |
+
"eval_steps_per_second": 2.537,
|
| 817 |
+
"eval_wer": 0.27050824497876885,
|
| 818 |
+
"step": 21600
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 110.0,
|
| 822 |
+
"learning_rate": 8.54468085106383e-06,
|
| 823 |
+
"loss": 0.0148,
|
| 824 |
+
"step": 22000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 110.0,
|
| 828 |
+
"eval_loss": 0.524269700050354,
|
| 829 |
+
"eval_runtime": 251.4198,
|
| 830 |
+
"eval_samples_per_second": 20.734,
|
| 831 |
+
"eval_steps_per_second": 2.593,
|
| 832 |
+
"eval_wer": 0.269075468257483,
|
| 833 |
+
"step": 22000
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 112.0,
|
| 837 |
+
"learning_rate": 6.846808510638299e-06,
|
| 838 |
+
"loss": 0.0142,
|
| 839 |
+
"step": 22400
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 112.0,
|
| 843 |
+
"eval_loss": 0.5115846991539001,
|
| 844 |
+
"eval_runtime": 252.9673,
|
| 845 |
+
"eval_samples_per_second": 20.607,
|
| 846 |
+
"eval_steps_per_second": 2.577,
|
| 847 |
+
"eval_wer": 0.269075468257483,
|
| 848 |
+
"step": 22400
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 114.0,
|
| 852 |
+
"learning_rate": 5.14468085106383e-06,
|
| 853 |
+
"loss": 0.0133,
|
| 854 |
+
"step": 22800
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 114.0,
|
| 858 |
+
"eval_loss": 0.5274414420127869,
|
| 859 |
+
"eval_runtime": 253.5713,
|
| 860 |
+
"eval_samples_per_second": 20.558,
|
| 861 |
+
"eval_steps_per_second": 2.571,
|
| 862 |
+
"eval_wer": 0.2676166410503556,
|
| 863 |
+
"step": 22800
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 116.0,
|
| 867 |
+
"learning_rate": 3.4425531914893614e-06,
|
| 868 |
+
"loss": 0.0138,
|
| 869 |
+
"step": 23200
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 116.0,
|
| 873 |
+
"eval_loss": 0.5216977596282959,
|
| 874 |
+
"eval_runtime": 253.8491,
|
| 875 |
+
"eval_samples_per_second": 20.536,
|
| 876 |
+
"eval_steps_per_second": 2.568,
|
| 877 |
+
"eval_wer": 0.26722588376273215,
|
| 878 |
+
"step": 23200
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 118.0,
|
| 882 |
+
"learning_rate": 1.7404255319148937e-06,
|
| 883 |
+
"loss": 0.0135,
|
| 884 |
+
"step": 23600
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 118.0,
|
| 888 |
+
"eval_loss": 0.5230008363723755,
|
| 889 |
+
"eval_runtime": 257.6327,
|
| 890 |
+
"eval_samples_per_second": 20.234,
|
| 891 |
+
"eval_steps_per_second": 2.531,
|
| 892 |
+
"eval_wer": 0.2673300857060984,
|
| 893 |
+
"step": 23600
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 120.0,
|
| 897 |
+
"learning_rate": 3.8297872340425535e-08,
|
| 898 |
+
"loss": 0.0134,
|
| 899 |
+
"step": 24000
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 120.0,
|
| 903 |
+
"eval_loss": 0.5197370648384094,
|
| 904 |
+
"eval_runtime": 253.9198,
|
| 905 |
+
"eval_samples_per_second": 20.53,
|
| 906 |
+
"eval_steps_per_second": 2.568,
|
| 907 |
+
"eval_wer": 0.2666527730742178,
|
| 908 |
+
"step": 24000
|
| 909 |
+
}
|
| 910 |
+
],
|
| 911 |
+
"max_steps": 24000,
|
| 912 |
+
"num_train_epochs": 120,
|
| 913 |
+
"total_flos": 1.951590305315055e+20,
|
| 914 |
+
"trial_name": null,
|
| 915 |
+
"trial_params": null
|
| 916 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fbd4d80b91239ccb59f3fd4c3d9a0971fbd7a93d783fbf38499a7e2b8aef470e
|
| 3 |
+
size 2991
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"آ": 1, "ئ": 2, "ا": 3, "ب": 4, "ت": 5, "ث": 6, "ج": 7, "ح": 8, "خ": 9, "د": 10, "ذ": 11, "ر": 12, "ز": 13, "س": 14, "ش": 15, "ص": 16, "ض": 17, "ط": 18, "ظ": 19, "ع": 20, "غ": 21, "ف": 22, "ق": 23, "ل": 24, "م": 25, "ن": 26, "ه": 27, "و": 28, "پ": 29, "چ": 30, "ژ": 31, "ک": 32, "گ": 33, "ی": 34, "": 35, "|": 0, "[UNK]": 36, "[PAD]": 37}
|