Upload folder using huggingface_hub
Browse files- .ipynb_checkpoints/trainer_state-checkpoint.json +111 -0
- added_tokens.json +4 -0
- config.json +82 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +10 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map-Copy1.json +6 -0
- special_tokens_map.json +6 -0
- tokenizer_config-Copy1.json +48 -0
- tokenizer_config.json +47 -0
- trainer_state.json +111 -0
- training_args.bin +3 -0
- vocab.json +40 -0
.ipynb_checkpoints/trainer_state-checkpoint.json
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.651884700665189,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 6000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.11,
|
| 13 |
+
"learning_rate": 1.994e-05,
|
| 14 |
+
"loss": 1.0646,
|
| 15 |
+
"step": 1000
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.11,
|
| 19 |
+
"eval_loss": 0.1494615077972412,
|
| 20 |
+
"eval_runtime": 282.0461,
|
| 21 |
+
"eval_samples_per_second": 32.062,
|
| 22 |
+
"eval_steps_per_second": 1.003,
|
| 23 |
+
"eval_wer": 0.10898120702366802,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.22,
|
| 28 |
+
"learning_rate": 2.965802752293578e-05,
|
| 29 |
+
"loss": 0.0739,
|
| 30 |
+
"step": 2000
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.22,
|
| 34 |
+
"eval_loss": 0.13595812022686005,
|
| 35 |
+
"eval_runtime": 283.0515,
|
| 36 |
+
"eval_samples_per_second": 31.948,
|
| 37 |
+
"eval_steps_per_second": 1.0,
|
| 38 |
+
"eval_wer": 0.09173801176629903,
|
| 39 |
+
"step": 2000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.33,
|
| 43 |
+
"learning_rate": 2.8969954128440366e-05,
|
| 44 |
+
"loss": 0.0523,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 3.33,
|
| 49 |
+
"eval_loss": 0.12313445657491684,
|
| 50 |
+
"eval_runtime": 284.3097,
|
| 51 |
+
"eval_samples_per_second": 31.807,
|
| 52 |
+
"eval_steps_per_second": 0.995,
|
| 53 |
+
"eval_wer": 0.08295090353741291,
|
| 54 |
+
"step": 3000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 4.43,
|
| 58 |
+
"learning_rate": 2.8281880733944955e-05,
|
| 59 |
+
"loss": 0.0403,
|
| 60 |
+
"step": 4000
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 4.43,
|
| 64 |
+
"eval_loss": 0.12026045471429825,
|
| 65 |
+
"eval_runtime": 284.5505,
|
| 66 |
+
"eval_samples_per_second": 31.78,
|
| 67 |
+
"eval_steps_per_second": 0.995,
|
| 68 |
+
"eval_wer": 0.07766961074916116,
|
| 69 |
+
"step": 4000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 5.54,
|
| 73 |
+
"learning_rate": 2.7594495412844036e-05,
|
| 74 |
+
"loss": 0.0316,
|
| 75 |
+
"step": 5000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 5.54,
|
| 79 |
+
"eval_loss": 0.12377411127090454,
|
| 80 |
+
"eval_runtime": 284.9055,
|
| 81 |
+
"eval_samples_per_second": 31.74,
|
| 82 |
+
"eval_steps_per_second": 0.993,
|
| 83 |
+
"eval_wer": 0.07822632822256662,
|
| 84 |
+
"step": 5000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 6.65,
|
| 88 |
+
"learning_rate": 2.6906422018348625e-05,
|
| 89 |
+
"loss": 0.0291,
|
| 90 |
+
"step": 6000
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 6.65,
|
| 94 |
+
"eval_loss": 0.13142403960227966,
|
| 95 |
+
"eval_runtime": 283.6473,
|
| 96 |
+
"eval_samples_per_second": 31.881,
|
| 97 |
+
"eval_steps_per_second": 0.998,
|
| 98 |
+
"eval_wer": 0.07968583078798092,
|
| 99 |
+
"step": 6000
|
| 100 |
+
}
|
| 101 |
+
],
|
| 102 |
+
"logging_steps": 1000,
|
| 103 |
+
"max_steps": 45100,
|
| 104 |
+
"num_input_tokens_seen": 0,
|
| 105 |
+
"num_train_epochs": 50,
|
| 106 |
+
"save_steps": 1000,
|
| 107 |
+
"total_flos": 2.956600942328697e+19,
|
| 108 |
+
"train_batch_size": 32,
|
| 109 |
+
"trial_name": null,
|
| 110 |
+
"trial_params": null
|
| 111 |
+
}
|
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s>": 39,
|
| 3 |
+
"<s>": 38
|
| 4 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/w2v-bert-2.0",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"adapter_act": "relu",
|
| 5 |
+
"adapter_kernel_size": 3,
|
| 6 |
+
"adapter_stride": 2,
|
| 7 |
+
"add_adapter": true,
|
| 8 |
+
"apply_spec_augment": false,
|
| 9 |
+
"architectures": [
|
| 10 |
+
"Wav2Vec2BertForCTC"
|
| 11 |
+
],
|
| 12 |
+
"attention_dropout": 0.0,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"classifier_proj_size": 768,
|
| 15 |
+
"codevector_dim": 768,
|
| 16 |
+
"conformer_conv_dropout": 0.1,
|
| 17 |
+
"contrastive_logits_temperature": 0.1,
|
| 18 |
+
"conv_depthwise_kernel_size": 31,
|
| 19 |
+
"ctc_loss_reduction": "mean",
|
| 20 |
+
"ctc_zero_infinity": true,
|
| 21 |
+
"diversity_loss_weight": 100,
|
| 22 |
+
"eos_token_id": 2,
|
| 23 |
+
"feat_proj_dropout": 0.0,
|
| 24 |
+
"feat_quantizer_dropout": 0.0,
|
| 25 |
+
"feature_projection_input_dim": 160,
|
| 26 |
+
"final_dropout": 0.1,
|
| 27 |
+
"hidden_act": "swish",
|
| 28 |
+
"hidden_dropout": 0.0,
|
| 29 |
+
"hidden_size": 1024,
|
| 30 |
+
"initializer_range": 0.02,
|
| 31 |
+
"intermediate_size": 4096,
|
| 32 |
+
"layer_norm_eps": 1e-05,
|
| 33 |
+
"layerdrop": 0.0,
|
| 34 |
+
"left_max_position_embeddings": 64,
|
| 35 |
+
"mask_feature_length": 10,
|
| 36 |
+
"mask_feature_min_masks": 0,
|
| 37 |
+
"mask_feature_prob": 0.0,
|
| 38 |
+
"mask_time_length": 10,
|
| 39 |
+
"mask_time_min_masks": 2,
|
| 40 |
+
"mask_time_prob": 0.0,
|
| 41 |
+
"max_source_positions": 5000,
|
| 42 |
+
"model_type": "wav2vec2-bert",
|
| 43 |
+
"num_adapter_layers": 1,
|
| 44 |
+
"num_attention_heads": 16,
|
| 45 |
+
"num_codevector_groups": 2,
|
| 46 |
+
"num_codevectors_per_group": 320,
|
| 47 |
+
"num_hidden_layers": 24,
|
| 48 |
+
"num_negatives": 100,
|
| 49 |
+
"output_hidden_size": 1024,
|
| 50 |
+
"pad_token_id": 37,
|
| 51 |
+
"position_embeddings_type": "relative_key",
|
| 52 |
+
"proj_codevector_dim": 768,
|
| 53 |
+
"right_max_position_embeddings": 8,
|
| 54 |
+
"rotary_embedding_base": 10000,
|
| 55 |
+
"tdnn_dilation": [
|
| 56 |
+
1,
|
| 57 |
+
2,
|
| 58 |
+
3,
|
| 59 |
+
1,
|
| 60 |
+
1
|
| 61 |
+
],
|
| 62 |
+
"tdnn_dim": [
|
| 63 |
+
512,
|
| 64 |
+
512,
|
| 65 |
+
512,
|
| 66 |
+
512,
|
| 67 |
+
1500
|
| 68 |
+
],
|
| 69 |
+
"tdnn_kernel": [
|
| 70 |
+
5,
|
| 71 |
+
3,
|
| 72 |
+
3,
|
| 73 |
+
1,
|
| 74 |
+
1
|
| 75 |
+
],
|
| 76 |
+
"torch_dtype": "float32",
|
| 77 |
+
"transformers_version": "4.37.1",
|
| 78 |
+
"use_intermediate_ffn_before_adapter": false,
|
| 79 |
+
"use_weighted_layer_sum": false,
|
| 80 |
+
"vocab_size": 40,
|
| 81 |
+
"xvector_output_dim": 512
|
| 82 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e88b4ed4b67d4954dff242f39cd9cd995b1ed42bc15c194e27ba2f36a5591d1
|
| 3 |
+
size 2422978560
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5e1f703fd1beac080cf24c3fb3c480d0694897f7393c791c4c56d65e97cf5d8
|
| 3 |
+
size 4846417898
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"feature_extractor_type": "SeamlessM4TFeatureExtractor",
|
| 3 |
+
"feature_size": 80,
|
| 4 |
+
"num_mel_bins": 80,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0.0,
|
| 7 |
+
"return_attention_mask": true,
|
| 8 |
+
"sampling_rate": 16000,
|
| 9 |
+
"stride": 2
|
| 10 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efd31c7c23c74f20a2ab3bd4b62e1e2dcf6afabce1ec901012b9fa96797be372
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6dce7bb04dabf1f1e4235c44bfa4f7838b335dc042139ffe978ce285277ef8fe
|
| 3 |
+
size 1064
|
special_tokens_map-Copy1.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"unk_token": "[UNK]"
|
| 6 |
+
}
|
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-Copy1.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"36": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": true,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": true,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": false
|
| 10 |
+
},
|
| 11 |
+
"37": {
|
| 12 |
+
"content": "[PAD]",
|
| 13 |
+
"lstrip": true,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": true,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": false
|
| 18 |
+
},
|
| 19 |
+
"38": {
|
| 20 |
+
"content": "<s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"39": {
|
| 28 |
+
"content": "</s>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 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": "Wav2Vec2BertProcessor",
|
| 43 |
+
"replace_word_delimiter_char": " ",
|
| 44 |
+
"target_lang": null,
|
| 45 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 46 |
+
"unk_token": "[UNK]",
|
| 47 |
+
"word_delimiter_token": "|"
|
| 48 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"36": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": true,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": true,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": false
|
| 10 |
+
},
|
| 11 |
+
"37": {
|
| 12 |
+
"content": "[PAD]",
|
| 13 |
+
"lstrip": true,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": true,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": false
|
| 18 |
+
},
|
| 19 |
+
"38": {
|
| 20 |
+
"content": "<s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"39": {
|
| 28 |
+
"content": "</s>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 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 |
+
"replace_word_delimiter_char": " ",
|
| 43 |
+
"target_lang": null,
|
| 44 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 45 |
+
"unk_token": "[UNK]",
|
| 46 |
+
"word_delimiter_token": "|"
|
| 47 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.651884700665189,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 6000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.11,
|
| 13 |
+
"learning_rate": 1.994e-05,
|
| 14 |
+
"loss": 1.0646,
|
| 15 |
+
"step": 1000
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.11,
|
| 19 |
+
"eval_loss": 0.1494615077972412,
|
| 20 |
+
"eval_runtime": 282.0461,
|
| 21 |
+
"eval_samples_per_second": 32.062,
|
| 22 |
+
"eval_steps_per_second": 1.003,
|
| 23 |
+
"eval_wer": 0.10898120702366802,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.22,
|
| 28 |
+
"learning_rate": 2.965802752293578e-05,
|
| 29 |
+
"loss": 0.0739,
|
| 30 |
+
"step": 2000
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.22,
|
| 34 |
+
"eval_loss": 0.13595812022686005,
|
| 35 |
+
"eval_runtime": 283.0515,
|
| 36 |
+
"eval_samples_per_second": 31.948,
|
| 37 |
+
"eval_steps_per_second": 1.0,
|
| 38 |
+
"eval_wer": 0.09173801176629903,
|
| 39 |
+
"step": 2000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.33,
|
| 43 |
+
"learning_rate": 2.8969954128440366e-05,
|
| 44 |
+
"loss": 0.0523,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 3.33,
|
| 49 |
+
"eval_loss": 0.12313445657491684,
|
| 50 |
+
"eval_runtime": 284.3097,
|
| 51 |
+
"eval_samples_per_second": 31.807,
|
| 52 |
+
"eval_steps_per_second": 0.995,
|
| 53 |
+
"eval_wer": 0.08295090353741291,
|
| 54 |
+
"step": 3000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 4.43,
|
| 58 |
+
"learning_rate": 2.8281880733944955e-05,
|
| 59 |
+
"loss": 0.0403,
|
| 60 |
+
"step": 4000
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 4.43,
|
| 64 |
+
"eval_loss": 0.12026045471429825,
|
| 65 |
+
"eval_runtime": 284.5505,
|
| 66 |
+
"eval_samples_per_second": 31.78,
|
| 67 |
+
"eval_steps_per_second": 0.995,
|
| 68 |
+
"eval_wer": 0.07766961074916116,
|
| 69 |
+
"step": 4000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 5.54,
|
| 73 |
+
"learning_rate": 2.7594495412844036e-05,
|
| 74 |
+
"loss": 0.0316,
|
| 75 |
+
"step": 5000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 5.54,
|
| 79 |
+
"eval_loss": 0.12377411127090454,
|
| 80 |
+
"eval_runtime": 284.9055,
|
| 81 |
+
"eval_samples_per_second": 31.74,
|
| 82 |
+
"eval_steps_per_second": 0.993,
|
| 83 |
+
"eval_wer": 0.07822632822256662,
|
| 84 |
+
"step": 5000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 6.65,
|
| 88 |
+
"learning_rate": 2.6906422018348625e-05,
|
| 89 |
+
"loss": 0.0291,
|
| 90 |
+
"step": 6000
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 6.65,
|
| 94 |
+
"eval_loss": 0.13142403960227966,
|
| 95 |
+
"eval_runtime": 283.6473,
|
| 96 |
+
"eval_samples_per_second": 31.881,
|
| 97 |
+
"eval_steps_per_second": 0.998,
|
| 98 |
+
"eval_wer": 0.07968583078798092,
|
| 99 |
+
"step": 6000
|
| 100 |
+
}
|
| 101 |
+
],
|
| 102 |
+
"logging_steps": 1000,
|
| 103 |
+
"max_steps": 45100,
|
| 104 |
+
"num_input_tokens_seen": 0,
|
| 105 |
+
"num_train_epochs": 50,
|
| 106 |
+
"save_steps": 1000,
|
| 107 |
+
"total_flos": 2.956600942328697e+19,
|
| 108 |
+
"train_batch_size": 32,
|
| 109 |
+
"trial_name": null,
|
| 110 |
+
"trial_params": null
|
| 111 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da06027d227b2be1264bd7efd41a9ecb4f4c18f7612a78cb13587316bd0e4e52
|
| 3 |
+
size 4728
|
vocab.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 37,
|
| 3 |
+
"[UNK]": 36,
|
| 4 |
+
"a": 1,
|
| 5 |
+
"b": 2,
|
| 6 |
+
"c": 3,
|
| 7 |
+
"d": 4,
|
| 8 |
+
"e": 5,
|
| 9 |
+
"f": 6,
|
| 10 |
+
"g": 7,
|
| 11 |
+
"h": 8,
|
| 12 |
+
"i": 9,
|
| 13 |
+
"j": 10,
|
| 14 |
+
"k": 11,
|
| 15 |
+
"l": 12,
|
| 16 |
+
"m": 13,
|
| 17 |
+
"n": 14,
|
| 18 |
+
"o": 15,
|
| 19 |
+
"p": 16,
|
| 20 |
+
"q": 17,
|
| 21 |
+
"r": 18,
|
| 22 |
+
"s": 19,
|
| 23 |
+
"t": 20,
|
| 24 |
+
"u": 21,
|
| 25 |
+
"v": 22,
|
| 26 |
+
"w": 23,
|
| 27 |
+
"x": 24,
|
| 28 |
+
"y": 25,
|
| 29 |
+
"z": 26,
|
| 30 |
+
"|": 0,
|
| 31 |
+
"ó": 27,
|
| 32 |
+
"ą": 28,
|
| 33 |
+
"ć": 29,
|
| 34 |
+
"ę": 30,
|
| 35 |
+
"ł": 31,
|
| 36 |
+
"ń": 32,
|
| 37 |
+
"ś": 33,
|
| 38 |
+
"ź": 34,
|
| 39 |
+
"ż": 35
|
| 40 |
+
}
|