Upload 10 files
Browse files- all_results.json +9 -0
- config.json +117 -0
- model.safetensors +3 -0
- preprocessor_config.json +10 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +48 -0
- train_results.json +9 -0
- trainer_state.json +285 -0
- training_args.bin +3 -0
- vocab.json +39 -0
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 4.297170075587716e+18,
|
| 4 |
+
"train_loss": 0.38818399047851565,
|
| 5 |
+
"train_runtime": 7019.9025,
|
| 6 |
+
"train_samples": 8000,
|
| 7 |
+
"train_samples_per_second": 3.419,
|
| 8 |
+
"train_steps_per_second": 0.214
|
| 9 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/content/drive/MyDrive/Graduation project/dataset/part 3/Models/asc_wav2vec2_large_xlsr_model_best_checkpoint/checkpoint-500",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"adapter_attn_dim": null,
|
| 5 |
+
"adapter_kernel_size": 3,
|
| 6 |
+
"adapter_stride": 2,
|
| 7 |
+
"add_adapter": false,
|
| 8 |
+
"apply_spec_augment": true,
|
| 9 |
+
"architectures": [
|
| 10 |
+
"Wav2Vec2ForCTC"
|
| 11 |
+
],
|
| 12 |
+
"attention_dropout": 0.0,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"classifier_proj_size": 256,
|
| 15 |
+
"codevector_dim": 768,
|
| 16 |
+
"contrastive_logits_temperature": 0.1,
|
| 17 |
+
"conv_bias": true,
|
| 18 |
+
"conv_dim": [
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512,
|
| 25 |
+
512
|
| 26 |
+
],
|
| 27 |
+
"conv_kernel": [
|
| 28 |
+
10,
|
| 29 |
+
3,
|
| 30 |
+
3,
|
| 31 |
+
3,
|
| 32 |
+
3,
|
| 33 |
+
2,
|
| 34 |
+
2
|
| 35 |
+
],
|
| 36 |
+
"conv_stride": [
|
| 37 |
+
5,
|
| 38 |
+
2,
|
| 39 |
+
2,
|
| 40 |
+
2,
|
| 41 |
+
2,
|
| 42 |
+
2,
|
| 43 |
+
2
|
| 44 |
+
],
|
| 45 |
+
"ctc_loss_reduction": "mean",
|
| 46 |
+
"ctc_zero_infinity": false,
|
| 47 |
+
"diversity_loss_weight": 0.1,
|
| 48 |
+
"do_stable_layer_norm": true,
|
| 49 |
+
"eos_token_id": 2,
|
| 50 |
+
"feat_extract_activation": "gelu",
|
| 51 |
+
"feat_extract_dropout": 0.0,
|
| 52 |
+
"feat_extract_norm": "layer",
|
| 53 |
+
"feat_proj_dropout": 0.0,
|
| 54 |
+
"feat_quantizer_dropout": 0.0,
|
| 55 |
+
"final_dropout": 0.0,
|
| 56 |
+
"gradient_checkpointing": false,
|
| 57 |
+
"hidden_act": "gelu",
|
| 58 |
+
"hidden_dropout": 0.0,
|
| 59 |
+
"hidden_size": 1024,
|
| 60 |
+
"initializer_range": 0.02,
|
| 61 |
+
"intermediate_size": 4096,
|
| 62 |
+
"layer_norm_eps": 1e-05,
|
| 63 |
+
"layerdrop": 0.0,
|
| 64 |
+
"mask_channel_length": 10,
|
| 65 |
+
"mask_channel_min_space": 1,
|
| 66 |
+
"mask_channel_other": 0.0,
|
| 67 |
+
"mask_channel_prob": 0.0,
|
| 68 |
+
"mask_channel_selection": "static",
|
| 69 |
+
"mask_feature_length": 10,
|
| 70 |
+
"mask_feature_min_masks": 0,
|
| 71 |
+
"mask_feature_prob": 0.0,
|
| 72 |
+
"mask_time_length": 10,
|
| 73 |
+
"mask_time_min_masks": 2,
|
| 74 |
+
"mask_time_min_space": 1,
|
| 75 |
+
"mask_time_other": 0.0,
|
| 76 |
+
"mask_time_prob": 0.05,
|
| 77 |
+
"mask_time_selection": "static",
|
| 78 |
+
"model_type": "wav2vec2",
|
| 79 |
+
"num_adapter_layers": 3,
|
| 80 |
+
"num_attention_heads": 16,
|
| 81 |
+
"num_codevector_groups": 2,
|
| 82 |
+
"num_codevectors_per_group": 320,
|
| 83 |
+
"num_conv_pos_embedding_groups": 16,
|
| 84 |
+
"num_conv_pos_embeddings": 128,
|
| 85 |
+
"num_feat_extract_layers": 7,
|
| 86 |
+
"num_hidden_layers": 24,
|
| 87 |
+
"num_negatives": 100,
|
| 88 |
+
"output_hidden_size": 1024,
|
| 89 |
+
"pad_token_id": 33,
|
| 90 |
+
"proj_codevector_dim": 768,
|
| 91 |
+
"tdnn_dilation": [
|
| 92 |
+
1,
|
| 93 |
+
2,
|
| 94 |
+
3,
|
| 95 |
+
1,
|
| 96 |
+
1
|
| 97 |
+
],
|
| 98 |
+
"tdnn_dim": [
|
| 99 |
+
512,
|
| 100 |
+
512,
|
| 101 |
+
512,
|
| 102 |
+
512,
|
| 103 |
+
1500
|
| 104 |
+
],
|
| 105 |
+
"tdnn_kernel": [
|
| 106 |
+
5,
|
| 107 |
+
3,
|
| 108 |
+
3,
|
| 109 |
+
1,
|
| 110 |
+
1
|
| 111 |
+
],
|
| 112 |
+
"torch_dtype": "float32",
|
| 113 |
+
"transformers_version": "4.40.2",
|
| 114 |
+
"use_weighted_layer_sum": false,
|
| 115 |
+
"vocab_size": 37,
|
| 116 |
+
"xvector_output_dim": 512
|
| 117 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:baee2c25314c5f4c7c77695a6a17aa0197209ca0f531b142980b0be8ff0afce9
|
| 3 |
+
size 1261959132
|
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,
|
| 7 |
+
"processor_class": "Wav2Vec2Processor",
|
| 8 |
+
"return_attention_mask": true,
|
| 9 |
+
"sampling_rate": 16000
|
| 10 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"33": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": true,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": true,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": false
|
| 10 |
+
},
|
| 11 |
+
"34": {
|
| 12 |
+
"content": "<unk>",
|
| 13 |
+
"lstrip": true,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": true,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": false
|
| 18 |
+
},
|
| 19 |
+
"35": {
|
| 20 |
+
"content": "<s>",
|
| 21 |
+
"lstrip": true,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": true,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": false
|
| 26 |
+
},
|
| 27 |
+
"36": {
|
| 28 |
+
"content": "</s>",
|
| 29 |
+
"lstrip": true,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": true,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"bos_token": "<s>",
|
| 37 |
+
"clean_up_tokenization_spaces": true,
|
| 38 |
+
"do_lower_case": false,
|
| 39 |
+
"eos_token": "</s>",
|
| 40 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 41 |
+
"pad_token": "<pad>",
|
| 42 |
+
"processor_class": "Wav2Vec2Processor",
|
| 43 |
+
"replace_word_delimiter_char": " ",
|
| 44 |
+
"target_lang": null,
|
| 45 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 46 |
+
"unk_token": "<unk>",
|
| 47 |
+
"word_delimiter_token": "|"
|
| 48 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 4.297170075587716e+18,
|
| 4 |
+
"train_loss": 0.38818399047851565,
|
| 5 |
+
"train_runtime": 7019.9025,
|
| 6 |
+
"train_samples": 8000,
|
| 7 |
+
"train_samples_per_second": 3.419,
|
| 8 |
+
"train_steps_per_second": 0.214
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,285 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.21690590111642744,
|
| 3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/Graduation project/dataset/part 3/Models/asc_wav2vec2_large_xlsr_model/checkpoint-500",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 2.2857142857142856,
|
| 13 |
+
"grad_norm": 0.21812936663627625,
|
| 14 |
+
"learning_rate": 0.00023,
|
| 15 |
+
"loss": 4.0688,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 2.2857142857142856,
|
| 20 |
+
"eval_cer": 1.0,
|
| 21 |
+
"eval_loss": 2.944187879562378,
|
| 22 |
+
"eval_runtime": 25.2241,
|
| 23 |
+
"eval_samples_per_second": 3.964,
|
| 24 |
+
"eval_steps_per_second": 3.964,
|
| 25 |
+
"eval_wer": 1.0,
|
| 26 |
+
"step": 100
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 4.571428571428571,
|
| 30 |
+
"grad_norm": 0.5214684009552002,
|
| 31 |
+
"learning_rate": 0.00023,
|
| 32 |
+
"loss": 1.9289,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 4.571428571428571,
|
| 37 |
+
"eval_cer": 0.09955781857162,
|
| 38 |
+
"eval_loss": 0.5113587379455566,
|
| 39 |
+
"eval_runtime": 24.8081,
|
| 40 |
+
"eval_samples_per_second": 4.031,
|
| 41 |
+
"eval_steps_per_second": 4.031,
|
| 42 |
+
"eval_wer": 0.4920255183413078,
|
| 43 |
+
"step": 200
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 6.857142857142857,
|
| 47 |
+
"grad_norm": 0.45686057209968567,
|
| 48 |
+
"learning_rate": 0.00023,
|
| 49 |
+
"loss": 0.3881,
|
| 50 |
+
"step": 300
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 6.857142857142857,
|
| 54 |
+
"eval_cer": 0.053463754522310065,
|
| 55 |
+
"eval_loss": 0.23284225165843964,
|
| 56 |
+
"eval_runtime": 24.918,
|
| 57 |
+
"eval_samples_per_second": 4.013,
|
| 58 |
+
"eval_steps_per_second": 4.013,
|
| 59 |
+
"eval_wer": 0.2711323763955343,
|
| 60 |
+
"step": 300
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 9.142857142857142,
|
| 64 |
+
"grad_norm": 0.3496246039867401,
|
| 65 |
+
"learning_rate": 0.00023,
|
| 66 |
+
"loss": 0.1989,
|
| 67 |
+
"step": 400
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 9.142857142857142,
|
| 71 |
+
"eval_cer": 0.05011389521640091,
|
| 72 |
+
"eval_loss": 0.20896148681640625,
|
| 73 |
+
"eval_runtime": 25.0682,
|
| 74 |
+
"eval_samples_per_second": 3.989,
|
| 75 |
+
"eval_steps_per_second": 3.989,
|
| 76 |
+
"eval_wer": 0.2567783094098884,
|
| 77 |
+
"step": 400
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 11.428571428571429,
|
| 81 |
+
"grad_norm": 1.072981357574463,
|
| 82 |
+
"learning_rate": 0.00023,
|
| 83 |
+
"loss": 0.1418,
|
| 84 |
+
"step": 500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 11.428571428571429,
|
| 88 |
+
"eval_cer": 0.041136272276564384,
|
| 89 |
+
"eval_loss": 0.1919952929019928,
|
| 90 |
+
"eval_runtime": 24.835,
|
| 91 |
+
"eval_samples_per_second": 4.027,
|
| 92 |
+
"eval_steps_per_second": 4.027,
|
| 93 |
+
"eval_wer": 0.21690590111642744,
|
| 94 |
+
"step": 500
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.2,
|
| 98 |
+
"grad_norm": 2.501166820526123,
|
| 99 |
+
"learning_rate": 0.00023,
|
| 100 |
+
"loss": 0.9766,
|
| 101 |
+
"step": 600
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.2,
|
| 105 |
+
"eval_cer": 0.22892712711125207,
|
| 106 |
+
"eval_loss": 0.7451229095458984,
|
| 107 |
+
"eval_runtime": 219.3212,
|
| 108 |
+
"eval_samples_per_second": 9.119,
|
| 109 |
+
"eval_steps_per_second": 9.119,
|
| 110 |
+
"eval_wer": 0.7126639264043845,
|
| 111 |
+
"step": 600
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.4,
|
| 115 |
+
"grad_norm": 2.21364688873291,
|
| 116 |
+
"learning_rate": 0.00023,
|
| 117 |
+
"loss": 0.7679,
|
| 118 |
+
"step": 700
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.4,
|
| 122 |
+
"eval_cer": 0.20032114820394895,
|
| 123 |
+
"eval_loss": 0.6842666864395142,
|
| 124 |
+
"eval_runtime": 220.1309,
|
| 125 |
+
"eval_samples_per_second": 9.086,
|
| 126 |
+
"eval_steps_per_second": 9.086,
|
| 127 |
+
"eval_wer": 0.6376981796829125,
|
| 128 |
+
"step": 700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.6,
|
| 132 |
+
"grad_norm": 1.8162668943405151,
|
| 133 |
+
"learning_rate": 0.00023,
|
| 134 |
+
"loss": 0.6767,
|
| 135 |
+
"step": 800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.6,
|
| 139 |
+
"eval_cer": 0.19177702006185077,
|
| 140 |
+
"eval_loss": 0.6032456159591675,
|
| 141 |
+
"eval_runtime": 218.5745,
|
| 142 |
+
"eval_samples_per_second": 9.15,
|
| 143 |
+
"eval_steps_per_second": 9.15,
|
| 144 |
+
"eval_wer": 0.6313368565276962,
|
| 145 |
+
"step": 800
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.8,
|
| 149 |
+
"grad_norm": 1.9325016736984253,
|
| 150 |
+
"learning_rate": 0.00023,
|
| 151 |
+
"loss": 0.6254,
|
| 152 |
+
"step": 900
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.8,
|
| 156 |
+
"eval_cer": 0.18921972880818333,
|
| 157 |
+
"eval_loss": 0.5750653147697449,
|
| 158 |
+
"eval_runtime": 221.3428,
|
| 159 |
+
"eval_samples_per_second": 9.036,
|
| 160 |
+
"eval_steps_per_second": 9.036,
|
| 161 |
+
"eval_wer": 0.6109806224310042,
|
| 162 |
+
"step": 900
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.0,
|
| 166 |
+
"grad_norm": 1.9160747528076172,
|
| 167 |
+
"learning_rate": 0.00023,
|
| 168 |
+
"loss": 0.6156,
|
| 169 |
+
"step": 1000
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 2.0,
|
| 173 |
+
"eval_cer": 0.1742526365871065,
|
| 174 |
+
"eval_loss": 0.5430945158004761,
|
| 175 |
+
"eval_runtime": 219.1129,
|
| 176 |
+
"eval_samples_per_second": 9.128,
|
| 177 |
+
"eval_steps_per_second": 9.128,
|
| 178 |
+
"eval_wer": 0.5729105500097866,
|
| 179 |
+
"step": 1000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.2,
|
| 183 |
+
"grad_norm": 1.2983200550079346,
|
| 184 |
+
"learning_rate": 0.00023,
|
| 185 |
+
"loss": 0.4506,
|
| 186 |
+
"step": 1100
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.2,
|
| 190 |
+
"eval_cer": 0.15419078582190152,
|
| 191 |
+
"eval_loss": 0.5200591087341309,
|
| 192 |
+
"eval_runtime": 220.7565,
|
| 193 |
+
"eval_samples_per_second": 9.06,
|
| 194 |
+
"eval_steps_per_second": 9.06,
|
| 195 |
+
"eval_wer": 0.5123311802701116,
|
| 196 |
+
"step": 1100
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 2.4,
|
| 200 |
+
"grad_norm": 1.5487444400787354,
|
| 201 |
+
"learning_rate": 0.00023,
|
| 202 |
+
"loss": 0.4399,
|
| 203 |
+
"step": 1200
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.4,
|
| 207 |
+
"eval_cer": 0.15298152406629134,
|
| 208 |
+
"eval_loss": 0.522709310054779,
|
| 209 |
+
"eval_runtime": 215.7214,
|
| 210 |
+
"eval_samples_per_second": 9.271,
|
| 211 |
+
"eval_steps_per_second": 9.271,
|
| 212 |
+
"eval_wer": 0.5041103934233705,
|
| 213 |
+
"step": 1200
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 2.6,
|
| 217 |
+
"grad_norm": 1.8711397647857666,
|
| 218 |
+
"learning_rate": 0.00023,
|
| 219 |
+
"loss": 0.4346,
|
| 220 |
+
"step": 1300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 2.6,
|
| 224 |
+
"eval_cer": 0.153219411624772,
|
| 225 |
+
"eval_loss": 0.5107786059379578,
|
| 226 |
+
"eval_runtime": 219.26,
|
| 227 |
+
"eval_samples_per_second": 9.122,
|
| 228 |
+
"eval_steps_per_second": 9.122,
|
| 229 |
+
"eval_wer": 0.5042082599334508,
|
| 230 |
+
"step": 1300
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.8,
|
| 234 |
+
"grad_norm": 1.684812068939209,
|
| 235 |
+
"learning_rate": 0.00023,
|
| 236 |
+
"loss": 0.4148,
|
| 237 |
+
"step": 1400
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.8,
|
| 241 |
+
"eval_cer": 0.14915549916739354,
|
| 242 |
+
"eval_loss": 0.5022586584091187,
|
| 243 |
+
"eval_runtime": 220.0102,
|
| 244 |
+
"eval_samples_per_second": 9.09,
|
| 245 |
+
"eval_steps_per_second": 9.09,
|
| 246 |
+
"eval_wer": 0.4847328244274809,
|
| 247 |
+
"step": 1400
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 3.0,
|
| 251 |
+
"grad_norm": 1.5067812204360962,
|
| 252 |
+
"learning_rate": 0.0,
|
| 253 |
+
"loss": 0.4207,
|
| 254 |
+
"step": 1500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.0,
|
| 258 |
+
"eval_cer": 0.1372809452065657,
|
| 259 |
+
"eval_loss": 0.4935847222805023,
|
| 260 |
+
"eval_runtime": 220.1042,
|
| 261 |
+
"eval_samples_per_second": 9.087,
|
| 262 |
+
"eval_steps_per_second": 9.087,
|
| 263 |
+
"eval_wer": 0.4493051477784302,
|
| 264 |
+
"step": 1500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 3.0,
|
| 268 |
+
"step": 1500,
|
| 269 |
+
"total_flos": 4.297170075587716e+18,
|
| 270 |
+
"train_loss": 0.38818399047851565,
|
| 271 |
+
"train_runtime": 7019.9025,
|
| 272 |
+
"train_samples_per_second": 3.419,
|
| 273 |
+
"train_steps_per_second": 0.214
|
| 274 |
+
}
|
| 275 |
+
],
|
| 276 |
+
"logging_steps": 100,
|
| 277 |
+
"max_steps": 1500,
|
| 278 |
+
"num_input_tokens_seen": 0,
|
| 279 |
+
"num_train_epochs": 3,
|
| 280 |
+
"save_steps": 500,
|
| 281 |
+
"total_flos": 4.297170075587716e+18,
|
| 282 |
+
"train_batch_size": 1,
|
| 283 |
+
"trial_name": null,
|
| 284 |
+
"trial_params": null
|
| 285 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82596a9c8fb6af194891732ad2b175dd343a33da383a91664ee63ad2d76cdacf
|
| 3 |
+
size 4655
|
vocab.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s>": 36,
|
| 3 |
+
"<pad>": 33,
|
| 4 |
+
"<s>": 35,
|
| 5 |
+
"<unk>": 34,
|
| 6 |
+
"|": 32,
|
| 7 |
+
"ء": 0,
|
| 8 |
+
"ؤ": 1,
|
| 9 |
+
"ئ": 2,
|
| 10 |
+
"ا": 3,
|
| 11 |
+
"ب": 4,
|
| 12 |
+
"ت": 5,
|
| 13 |
+
"ث": 6,
|
| 14 |
+
"ج": 7,
|
| 15 |
+
"ح": 8,
|
| 16 |
+
"خ": 9,
|
| 17 |
+
"د": 10,
|
| 18 |
+
"ذ": 11,
|
| 19 |
+
"ر": 12,
|
| 20 |
+
"ز": 13,
|
| 21 |
+
"س": 14,
|
| 22 |
+
"ش": 15,
|
| 23 |
+
"ص": 16,
|
| 24 |
+
"ض": 17,
|
| 25 |
+
"ط": 18,
|
| 26 |
+
"ظ": 19,
|
| 27 |
+
"ع": 20,
|
| 28 |
+
"غ": 21,
|
| 29 |
+
"ف": 22,
|
| 30 |
+
"ق": 23,
|
| 31 |
+
"ك": 24,
|
| 32 |
+
"ل": 25,
|
| 33 |
+
"م": 26,
|
| 34 |
+
"ن": 27,
|
| 35 |
+
"ه": 28,
|
| 36 |
+
"و": 29,
|
| 37 |
+
"ى": 30,
|
| 38 |
+
"ي": 31
|
| 39 |
+
}
|