Model upload 1e-4
Browse files- config.json +116 -0
- preprocessor_config.json +10 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +964 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
|
| 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": 0.1,
|
| 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 |
+
"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_channel_length": 10,
|
| 64 |
+
"mask_channel_min_space": 1,
|
| 65 |
+
"mask_channel_other": 0.0,
|
| 66 |
+
"mask_channel_prob": 0.0,
|
| 67 |
+
"mask_channel_selection": "static",
|
| 68 |
+
"mask_feature_length": 10,
|
| 69 |
+
"mask_feature_min_masks": 0,
|
| 70 |
+
"mask_feature_prob": 0.0,
|
| 71 |
+
"mask_time_length": 10,
|
| 72 |
+
"mask_time_min_masks": 2,
|
| 73 |
+
"mask_time_min_space": 1,
|
| 74 |
+
"mask_time_other": 0.0,
|
| 75 |
+
"mask_time_prob": 0.05,
|
| 76 |
+
"mask_time_selection": "static",
|
| 77 |
+
"model_type": "wav2vec2",
|
| 78 |
+
"num_adapter_layers": 3,
|
| 79 |
+
"num_attention_heads": 16,
|
| 80 |
+
"num_codevector_groups": 2,
|
| 81 |
+
"num_codevectors_per_group": 320,
|
| 82 |
+
"num_conv_pos_embedding_groups": 16,
|
| 83 |
+
"num_conv_pos_embeddings": 128,
|
| 84 |
+
"num_feat_extract_layers": 7,
|
| 85 |
+
"num_hidden_layers": 24,
|
| 86 |
+
"num_negatives": 100,
|
| 87 |
+
"output_hidden_size": 1024,
|
| 88 |
+
"pad_token_id": 99,
|
| 89 |
+
"proj_codevector_dim": 768,
|
| 90 |
+
"tdnn_dilation": [
|
| 91 |
+
1,
|
| 92 |
+
2,
|
| 93 |
+
3,
|
| 94 |
+
1,
|
| 95 |
+
1
|
| 96 |
+
],
|
| 97 |
+
"tdnn_dim": [
|
| 98 |
+
512,
|
| 99 |
+
512,
|
| 100 |
+
512,
|
| 101 |
+
512,
|
| 102 |
+
1500
|
| 103 |
+
],
|
| 104 |
+
"tdnn_kernel": [
|
| 105 |
+
5,
|
| 106 |
+
3,
|
| 107 |
+
3,
|
| 108 |
+
1,
|
| 109 |
+
1
|
| 110 |
+
],
|
| 111 |
+
"torch_dtype": "float32",
|
| 112 |
+
"transformers_version": "4.34.0",
|
| 113 |
+
"use_weighted_layer_sum": false,
|
| 114 |
+
"vocab_size": 102,
|
| 115 |
+
"xvector_output_dim": 512
|
| 116 |
+
}
|
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 sha256:2b1550b952e7f1560628473d04f7f7335d2655fa97b07cd0385ab9030642f632
|
| 3 |
+
size 1262320554
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d4b0eaa431685a9817c24fb51a02de489d68aec66d26bf130308c4147312438
|
| 3 |
+
size 14308
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:727ca7d1ae9dea6ca42f17c18de43b192f785e31307c04317d4130e5a3196885
|
| 3 |
+
size 1000
|
trainer_state.json
ADDED
|
@@ -0,0 +1,964 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 59.57446808510638,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 12600,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.95,
|
| 13 |
+
"learning_rate": 3.9200000000000004e-05,
|
| 14 |
+
"loss": 17.3127,
|
| 15 |
+
"step": 200
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.95,
|
| 19 |
+
"eval_loss": 5.568685531616211,
|
| 20 |
+
"eval_runtime": 103.0983,
|
| 21 |
+
"eval_samples_per_second": 28.584,
|
| 22 |
+
"eval_steps_per_second": 3.579,
|
| 23 |
+
"eval_wer": 1.0,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.89,
|
| 28 |
+
"learning_rate": 7.920000000000001e-05,
|
| 29 |
+
"loss": 3.8015,
|
| 30 |
+
"step": 400
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.89,
|
| 34 |
+
"eval_loss": 3.4598944187164307,
|
| 35 |
+
"eval_runtime": 97.324,
|
| 36 |
+
"eval_samples_per_second": 30.28,
|
| 37 |
+
"eval_steps_per_second": 3.791,
|
| 38 |
+
"eval_wer": 1.0,
|
| 39 |
+
"step": 400
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.84,
|
| 43 |
+
"learning_rate": 9.921052631578947e-05,
|
| 44 |
+
"loss": 3.4087,
|
| 45 |
+
"step": 600
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 2.84,
|
| 49 |
+
"eval_loss": 3.372584581375122,
|
| 50 |
+
"eval_runtime": 97.3453,
|
| 51 |
+
"eval_samples_per_second": 30.274,
|
| 52 |
+
"eval_steps_per_second": 3.791,
|
| 53 |
+
"eval_wer": 1.0,
|
| 54 |
+
"step": 600
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.78,
|
| 58 |
+
"learning_rate": 9.756578947368421e-05,
|
| 59 |
+
"loss": 3.0965,
|
| 60 |
+
"step": 800
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 3.78,
|
| 64 |
+
"eval_loss": 1.8918038606643677,
|
| 65 |
+
"eval_runtime": 97.5597,
|
| 66 |
+
"eval_samples_per_second": 30.207,
|
| 67 |
+
"eval_steps_per_second": 3.782,
|
| 68 |
+
"eval_wer": 1.0220335473182853,
|
| 69 |
+
"step": 800
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.73,
|
| 73 |
+
"learning_rate": 9.592105263157895e-05,
|
| 74 |
+
"loss": 1.268,
|
| 75 |
+
"step": 1000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 4.73,
|
| 79 |
+
"eval_loss": 0.871788501739502,
|
| 80 |
+
"eval_runtime": 97.371,
|
| 81 |
+
"eval_samples_per_second": 30.266,
|
| 82 |
+
"eval_steps_per_second": 3.79,
|
| 83 |
+
"eval_wer": 0.7296748809277283,
|
| 84 |
+
"step": 1000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 5.67,
|
| 88 |
+
"learning_rate": 9.427631578947369e-05,
|
| 89 |
+
"loss": 0.7909,
|
| 90 |
+
"step": 1200
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 5.67,
|
| 94 |
+
"eval_loss": 0.7251957654953003,
|
| 95 |
+
"eval_runtime": 97.8397,
|
| 96 |
+
"eval_samples_per_second": 30.121,
|
| 97 |
+
"eval_steps_per_second": 3.771,
|
| 98 |
+
"eval_wer": 0.6389728722302754,
|
| 99 |
+
"step": 1200
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 6.62,
|
| 103 |
+
"learning_rate": 9.263157894736843e-05,
|
| 104 |
+
"loss": 0.6465,
|
| 105 |
+
"step": 1400
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 6.62,
|
| 109 |
+
"eval_loss": 0.6565062999725342,
|
| 110 |
+
"eval_runtime": 98.4682,
|
| 111 |
+
"eval_samples_per_second": 29.928,
|
| 112 |
+
"eval_steps_per_second": 3.747,
|
| 113 |
+
"eval_wer": 0.5930834541312902,
|
| 114 |
+
"step": 1400
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 7.57,
|
| 118 |
+
"learning_rate": 9.098684210526317e-05,
|
| 119 |
+
"loss": 0.5483,
|
| 120 |
+
"step": 1600
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 7.57,
|
| 124 |
+
"eval_loss": 0.6099365949630737,
|
| 125 |
+
"eval_runtime": 97.9877,
|
| 126 |
+
"eval_samples_per_second": 30.075,
|
| 127 |
+
"eval_steps_per_second": 3.766,
|
| 128 |
+
"eval_wer": 0.5626009525781736,
|
| 129 |
+
"step": 1600
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 8.51,
|
| 133 |
+
"learning_rate": 8.934210526315789e-05,
|
| 134 |
+
"loss": 0.4824,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 8.51,
|
| 139 |
+
"eval_loss": 0.5920658111572266,
|
| 140 |
+
"eval_runtime": 98.6224,
|
| 141 |
+
"eval_samples_per_second": 29.882,
|
| 142 |
+
"eval_steps_per_second": 3.742,
|
| 143 |
+
"eval_wer": 0.5455373783392007,
|
| 144 |
+
"step": 1800
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 9.46,
|
| 148 |
+
"learning_rate": 8.769736842105264e-05,
|
| 149 |
+
"loss": 0.4449,
|
| 150 |
+
"step": 2000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 9.46,
|
| 154 |
+
"eval_loss": 0.5740370750427246,
|
| 155 |
+
"eval_runtime": 98.609,
|
| 156 |
+
"eval_samples_per_second": 29.886,
|
| 157 |
+
"eval_steps_per_second": 3.742,
|
| 158 |
+
"eval_wer": 0.5382480844895423,
|
| 159 |
+
"step": 2000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 10.4,
|
| 163 |
+
"learning_rate": 8.605263157894738e-05,
|
| 164 |
+
"loss": 0.4106,
|
| 165 |
+
"step": 2200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 10.4,
|
| 169 |
+
"eval_loss": 0.5488039255142212,
|
| 170 |
+
"eval_runtime": 99.1998,
|
| 171 |
+
"eval_samples_per_second": 29.708,
|
| 172 |
+
"eval_steps_per_second": 3.72,
|
| 173 |
+
"eval_wer": 0.52238558707807,
|
| 174 |
+
"step": 2200
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 11.35,
|
| 178 |
+
"learning_rate": 8.44078947368421e-05,
|
| 179 |
+
"loss": 0.3835,
|
| 180 |
+
"step": 2400
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 11.35,
|
| 184 |
+
"eval_loss": 0.5332208275794983,
|
| 185 |
+
"eval_runtime": 98.9207,
|
| 186 |
+
"eval_samples_per_second": 29.792,
|
| 187 |
+
"eval_steps_per_second": 3.73,
|
| 188 |
+
"eval_wer": 0.5073514185131497,
|
| 189 |
+
"step": 2400
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 12.29,
|
| 193 |
+
"learning_rate": 8.276315789473684e-05,
|
| 194 |
+
"loss": 0.355,
|
| 195 |
+
"step": 2600
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 12.29,
|
| 199 |
+
"eval_loss": 0.5386897325515747,
|
| 200 |
+
"eval_runtime": 99.0067,
|
| 201 |
+
"eval_samples_per_second": 29.766,
|
| 202 |
+
"eval_steps_per_second": 3.727,
|
| 203 |
+
"eval_wer": 0.5013046179333195,
|
| 204 |
+
"step": 2600
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 13.24,
|
| 208 |
+
"learning_rate": 8.111842105263158e-05,
|
| 209 |
+
"loss": 0.3364,
|
| 210 |
+
"step": 2800
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 13.24,
|
| 214 |
+
"eval_loss": 0.553865373134613,
|
| 215 |
+
"eval_runtime": 98.276,
|
| 216 |
+
"eval_samples_per_second": 29.987,
|
| 217 |
+
"eval_steps_per_second": 3.755,
|
| 218 |
+
"eval_wer": 0.49662455995030025,
|
| 219 |
+
"step": 2800
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 14.18,
|
| 223 |
+
"learning_rate": 7.947368421052632e-05,
|
| 224 |
+
"loss": 0.3267,
|
| 225 |
+
"step": 3000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 14.18,
|
| 229 |
+
"eval_loss": 0.5239475965499878,
|
| 230 |
+
"eval_runtime": 98.3443,
|
| 231 |
+
"eval_samples_per_second": 29.966,
|
| 232 |
+
"eval_steps_per_second": 3.752,
|
| 233 |
+
"eval_wer": 0.49148892110167736,
|
| 234 |
+
"step": 3000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 15.13,
|
| 238 |
+
"learning_rate": 7.782894736842106e-05,
|
| 239 |
+
"loss": 0.312,
|
| 240 |
+
"step": 3200
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 15.13,
|
| 244 |
+
"eval_loss": 0.5197941064834595,
|
| 245 |
+
"eval_runtime": 99.0276,
|
| 246 |
+
"eval_samples_per_second": 29.759,
|
| 247 |
+
"eval_steps_per_second": 3.726,
|
| 248 |
+
"eval_wer": 0.4830813833091737,
|
| 249 |
+
"step": 3200
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 16.08,
|
| 253 |
+
"learning_rate": 7.61842105263158e-05,
|
| 254 |
+
"loss": 0.2835,
|
| 255 |
+
"step": 3400
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 16.08,
|
| 259 |
+
"eval_loss": 0.5393648147583008,
|
| 260 |
+
"eval_runtime": 99.0059,
|
| 261 |
+
"eval_samples_per_second": 29.766,
|
| 262 |
+
"eval_steps_per_second": 3.727,
|
| 263 |
+
"eval_wer": 0.4880099399461586,
|
| 264 |
+
"step": 3400
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 17.02,
|
| 268 |
+
"learning_rate": 7.453947368421052e-05,
|
| 269 |
+
"loss": 0.283,
|
| 270 |
+
"step": 3600
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 17.02,
|
| 274 |
+
"eval_loss": 0.5069576501846313,
|
| 275 |
+
"eval_runtime": 98.5638,
|
| 276 |
+
"eval_samples_per_second": 29.899,
|
| 277 |
+
"eval_steps_per_second": 3.744,
|
| 278 |
+
"eval_wer": 0.4773244978256368,
|
| 279 |
+
"step": 3600
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 17.97,
|
| 283 |
+
"learning_rate": 7.289473684210527e-05,
|
| 284 |
+
"loss": 0.2667,
|
| 285 |
+
"step": 3800
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 17.97,
|
| 289 |
+
"eval_loss": 0.5272166728973389,
|
| 290 |
+
"eval_runtime": 98.5512,
|
| 291 |
+
"eval_samples_per_second": 29.903,
|
| 292 |
+
"eval_steps_per_second": 3.744,
|
| 293 |
+
"eval_wer": 0.47583350590184303,
|
| 294 |
+
"step": 3800
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 18.91,
|
| 298 |
+
"learning_rate": 7.125000000000001e-05,
|
| 299 |
+
"loss": 0.2581,
|
| 300 |
+
"step": 4000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 18.91,
|
| 304 |
+
"eval_loss": 0.5214602947235107,
|
| 305 |
+
"eval_runtime": 98.4833,
|
| 306 |
+
"eval_samples_per_second": 29.924,
|
| 307 |
+
"eval_steps_per_second": 3.747,
|
| 308 |
+
"eval_wer": 0.4733485193621868,
|
| 309 |
+
"step": 4000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 19.86,
|
| 313 |
+
"learning_rate": 6.960526315789474e-05,
|
| 314 |
+
"loss": 0.249,
|
| 315 |
+
"step": 4200
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 19.86,
|
| 319 |
+
"eval_loss": 0.5193012952804565,
|
| 320 |
+
"eval_runtime": 98.3698,
|
| 321 |
+
"eval_samples_per_second": 29.958,
|
| 322 |
+
"eval_steps_per_second": 3.751,
|
| 323 |
+
"eval_wer": 0.4731828535928764,
|
| 324 |
+
"step": 4200
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 20.8,
|
| 328 |
+
"learning_rate": 6.796052631578947e-05,
|
| 329 |
+
"loss": 0.2423,
|
| 330 |
+
"step": 4400
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 20.8,
|
| 334 |
+
"eval_loss": 0.5255588889122009,
|
| 335 |
+
"eval_runtime": 98.8258,
|
| 336 |
+
"eval_samples_per_second": 29.82,
|
| 337 |
+
"eval_steps_per_second": 3.734,
|
| 338 |
+
"eval_wer": 0.47293435493891073,
|
| 339 |
+
"step": 4400
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 21.75,
|
| 343 |
+
"learning_rate": 6.631578947368421e-05,
|
| 344 |
+
"loss": 0.2337,
|
| 345 |
+
"step": 4600
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 21.75,
|
| 349 |
+
"eval_loss": 0.5264955163002014,
|
| 350 |
+
"eval_runtime": 98.5778,
|
| 351 |
+
"eval_samples_per_second": 29.895,
|
| 352 |
+
"eval_steps_per_second": 3.743,
|
| 353 |
+
"eval_wer": 0.4662248912818389,
|
| 354 |
+
"step": 4600
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 22.7,
|
| 358 |
+
"learning_rate": 6.467105263157895e-05,
|
| 359 |
+
"loss": 0.2176,
|
| 360 |
+
"step": 4800
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 22.7,
|
| 364 |
+
"eval_loss": 0.5588347315788269,
|
| 365 |
+
"eval_runtime": 99.5679,
|
| 366 |
+
"eval_samples_per_second": 29.598,
|
| 367 |
+
"eval_steps_per_second": 3.706,
|
| 368 |
+
"eval_wer": 0.4658521433008905,
|
| 369 |
+
"step": 4800
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 23.64,
|
| 373 |
+
"learning_rate": 6.302631578947369e-05,
|
| 374 |
+
"loss": 0.2184,
|
| 375 |
+
"step": 5000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 23.64,
|
| 379 |
+
"eval_loss": 0.5281316041946411,
|
| 380 |
+
"eval_runtime": 98.9467,
|
| 381 |
+
"eval_samples_per_second": 29.784,
|
| 382 |
+
"eval_steps_per_second": 3.729,
|
| 383 |
+
"eval_wer": 0.4603023400289915,
|
| 384 |
+
"step": 5000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 24.59,
|
| 388 |
+
"learning_rate": 6.138157894736843e-05,
|
| 389 |
+
"loss": 0.2093,
|
| 390 |
+
"step": 5200
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 24.59,
|
| 394 |
+
"eval_loss": 0.5339261293411255,
|
| 395 |
+
"eval_runtime": 99.0129,
|
| 396 |
+
"eval_samples_per_second": 29.764,
|
| 397 |
+
"eval_steps_per_second": 3.727,
|
| 398 |
+
"eval_wer": 0.45889418098985296,
|
| 399 |
+
"step": 5200
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 25.53,
|
| 403 |
+
"learning_rate": 5.973684210526316e-05,
|
| 404 |
+
"loss": 0.2022,
|
| 405 |
+
"step": 5400
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 25.53,
|
| 409 |
+
"eval_loss": 0.5497910976409912,
|
| 410 |
+
"eval_runtime": 98.8772,
|
| 411 |
+
"eval_samples_per_second": 29.805,
|
| 412 |
+
"eval_steps_per_second": 3.732,
|
| 413 |
+
"eval_wer": 0.46071650445226753,
|
| 414 |
+
"step": 5400
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 26.48,
|
| 418 |
+
"learning_rate": 5.809210526315789e-05,
|
| 419 |
+
"loss": 0.1961,
|
| 420 |
+
"step": 5600
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 26.48,
|
| 424 |
+
"eval_loss": 0.5337634682655334,
|
| 425 |
+
"eval_runtime": 99.299,
|
| 426 |
+
"eval_samples_per_second": 29.678,
|
| 427 |
+
"eval_steps_per_second": 3.716,
|
| 428 |
+
"eval_wer": 0.45553944916131706,
|
| 429 |
+
"step": 5600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 27.42,
|
| 433 |
+
"learning_rate": 5.6447368421052634e-05,
|
| 434 |
+
"loss": 0.1919,
|
| 435 |
+
"step": 5800
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 27.42,
|
| 439 |
+
"eval_loss": 0.5612215399742126,
|
| 440 |
+
"eval_runtime": 100.2927,
|
| 441 |
+
"eval_samples_per_second": 29.384,
|
| 442 |
+
"eval_steps_per_second": 3.679,
|
| 443 |
+
"eval_wer": 0.4570718575274384,
|
| 444 |
+
"step": 5800
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 28.37,
|
| 448 |
+
"learning_rate": 5.480263157894737e-05,
|
| 449 |
+
"loss": 0.183,
|
| 450 |
+
"step": 6000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 28.37,
|
| 454 |
+
"eval_loss": 0.5516127347946167,
|
| 455 |
+
"eval_runtime": 98.4866,
|
| 456 |
+
"eval_samples_per_second": 29.923,
|
| 457 |
+
"eval_steps_per_second": 3.747,
|
| 458 |
+
"eval_wer": 0.4569890246427832,
|
| 459 |
+
"step": 6000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 29.31,
|
| 463 |
+
"learning_rate": 5.3157894736842104e-05,
|
| 464 |
+
"loss": 0.1799,
|
| 465 |
+
"step": 6200
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 29.31,
|
| 469 |
+
"eval_loss": 0.5653464198112488,
|
| 470 |
+
"eval_runtime": 98.9685,
|
| 471 |
+
"eval_samples_per_second": 29.777,
|
| 472 |
+
"eval_steps_per_second": 3.728,
|
| 473 |
+
"eval_wer": 0.4539656243528681,
|
| 474 |
+
"step": 6200
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 30.26,
|
| 478 |
+
"learning_rate": 5.151315789473684e-05,
|
| 479 |
+
"loss": 0.1724,
|
| 480 |
+
"step": 6400
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 30.26,
|
| 484 |
+
"eval_loss": 0.5827488303184509,
|
| 485 |
+
"eval_runtime": 99.0205,
|
| 486 |
+
"eval_samples_per_second": 29.762,
|
| 487 |
+
"eval_steps_per_second": 3.727,
|
| 488 |
+
"eval_wer": 0.4514392213708842,
|
| 489 |
+
"step": 6400
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 31.21,
|
| 493 |
+
"learning_rate": 4.986842105263158e-05,
|
| 494 |
+
"loss": 0.1736,
|
| 495 |
+
"step": 6600
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 31.21,
|
| 499 |
+
"eval_loss": 0.5708160400390625,
|
| 500 |
+
"eval_runtime": 98.3383,
|
| 501 |
+
"eval_samples_per_second": 29.968,
|
| 502 |
+
"eval_steps_per_second": 3.752,
|
| 503 |
+
"eval_wer": 0.4497825636777801,
|
| 504 |
+
"step": 6600
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 32.15,
|
| 508 |
+
"learning_rate": 4.822368421052631e-05,
|
| 509 |
+
"loss": 0.1662,
|
| 510 |
+
"step": 6800
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 32.15,
|
| 514 |
+
"eval_loss": 0.5754191279411316,
|
| 515 |
+
"eval_runtime": 98.1735,
|
| 516 |
+
"eval_samples_per_second": 30.018,
|
| 517 |
+
"eval_steps_per_second": 3.759,
|
| 518 |
+
"eval_wer": 0.4442327604058811,
|
| 519 |
+
"step": 6800
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 33.1,
|
| 523 |
+
"learning_rate": 4.657894736842106e-05,
|
| 524 |
+
"loss": 0.1666,
|
| 525 |
+
"step": 7000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 33.1,
|
| 529 |
+
"eval_loss": 0.5671477913856506,
|
| 530 |
+
"eval_runtime": 98.673,
|
| 531 |
+
"eval_samples_per_second": 29.866,
|
| 532 |
+
"eval_steps_per_second": 3.74,
|
| 533 |
+
"eval_wer": 0.44460550838682955,
|
| 534 |
+
"step": 7000
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 34.04,
|
| 538 |
+
"learning_rate": 4.493421052631579e-05,
|
| 539 |
+
"loss": 0.1586,
|
| 540 |
+
"step": 7200
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 34.04,
|
| 544 |
+
"eval_loss": 0.5737903714179993,
|
| 545 |
+
"eval_runtime": 98.3986,
|
| 546 |
+
"eval_samples_per_second": 29.95,
|
| 547 |
+
"eval_steps_per_second": 3.75,
|
| 548 |
+
"eval_wer": 0.44642783184924417,
|
| 549 |
+
"step": 7200
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 34.99,
|
| 553 |
+
"learning_rate": 4.328947368421053e-05,
|
| 554 |
+
"loss": 0.154,
|
| 555 |
+
"step": 7400
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 34.99,
|
| 559 |
+
"eval_loss": 0.5759162902832031,
|
| 560 |
+
"eval_runtime": 99.171,
|
| 561 |
+
"eval_samples_per_second": 29.716,
|
| 562 |
+
"eval_steps_per_second": 3.721,
|
| 563 |
+
"eval_wer": 0.4414992752122593,
|
| 564 |
+
"step": 7400
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 35.93,
|
| 568 |
+
"learning_rate": 4.1644736842105265e-05,
|
| 569 |
+
"loss": 0.1515,
|
| 570 |
+
"step": 7600
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 35.93,
|
| 574 |
+
"eval_loss": 0.5758457779884338,
|
| 575 |
+
"eval_runtime": 98.2053,
|
| 576 |
+
"eval_samples_per_second": 30.009,
|
| 577 |
+
"eval_steps_per_second": 3.757,
|
| 578 |
+
"eval_wer": 0.445185338579416,
|
| 579 |
+
"step": 7600
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 36.88,
|
| 583 |
+
"learning_rate": 4e-05,
|
| 584 |
+
"loss": 0.1552,
|
| 585 |
+
"step": 7800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 36.88,
|
| 589 |
+
"eval_loss": 0.5782187581062317,
|
| 590 |
+
"eval_runtime": 98.8215,
|
| 591 |
+
"eval_samples_per_second": 29.821,
|
| 592 |
+
"eval_steps_per_second": 3.734,
|
| 593 |
+
"eval_wer": 0.44249326982812176,
|
| 594 |
+
"step": 7800
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 37.83,
|
| 598 |
+
"learning_rate": 3.835526315789474e-05,
|
| 599 |
+
"loss": 0.1471,
|
| 600 |
+
"step": 8000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 37.83,
|
| 604 |
+
"eval_loss": 0.5815852880477905,
|
| 605 |
+
"eval_runtime": 98.7527,
|
| 606 |
+
"eval_samples_per_second": 29.842,
|
| 607 |
+
"eval_steps_per_second": 3.737,
|
| 608 |
+
"eval_wer": 0.44187202319320773,
|
| 609 |
+
"step": 8000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 38.77,
|
| 613 |
+
"learning_rate": 3.671052631578947e-05,
|
| 614 |
+
"loss": 0.1413,
|
| 615 |
+
"step": 8200
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 38.77,
|
| 619 |
+
"eval_loss": 0.5855460166931152,
|
| 620 |
+
"eval_runtime": 98.45,
|
| 621 |
+
"eval_samples_per_second": 29.934,
|
| 622 |
+
"eval_steps_per_second": 3.748,
|
| 623 |
+
"eval_wer": 0.4429074342513978,
|
| 624 |
+
"step": 8200
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 39.72,
|
| 628 |
+
"learning_rate": 3.506578947368421e-05,
|
| 629 |
+
"loss": 0.1443,
|
| 630 |
+
"step": 8400
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 39.72,
|
| 634 |
+
"eval_loss": 0.5851101279258728,
|
| 635 |
+
"eval_runtime": 98.4835,
|
| 636 |
+
"eval_samples_per_second": 29.924,
|
| 637 |
+
"eval_steps_per_second": 3.747,
|
| 638 |
+
"eval_wer": 0.43731621453717123,
|
| 639 |
+
"step": 8400
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 40.66,
|
| 643 |
+
"learning_rate": 3.342927631578948e-05,
|
| 644 |
+
"loss": 0.1391,
|
| 645 |
+
"step": 8600
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 40.66,
|
| 649 |
+
"eval_loss": 0.5925698280334473,
|
| 650 |
+
"eval_runtime": 98.7707,
|
| 651 |
+
"eval_samples_per_second": 29.837,
|
| 652 |
+
"eval_steps_per_second": 3.736,
|
| 653 |
+
"eval_wer": 0.4420376889625181,
|
| 654 |
+
"step": 8600
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 41.61,
|
| 658 |
+
"learning_rate": 3.178453947368421e-05,
|
| 659 |
+
"loss": 0.1388,
|
| 660 |
+
"step": 8800
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 41.61,
|
| 664 |
+
"eval_loss": 0.5927318334579468,
|
| 665 |
+
"eval_runtime": 98.7868,
|
| 666 |
+
"eval_samples_per_second": 29.832,
|
| 667 |
+
"eval_steps_per_second": 3.735,
|
| 668 |
+
"eval_wer": 0.43636363636363634,
|
| 669 |
+
"step": 8800
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 42.55,
|
| 673 |
+
"learning_rate": 3.013980263157895e-05,
|
| 674 |
+
"loss": 0.1419,
|
| 675 |
+
"step": 9000
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 42.55,
|
| 679 |
+
"eval_loss": 0.5933807492256165,
|
| 680 |
+
"eval_runtime": 98.9246,
|
| 681 |
+
"eval_samples_per_second": 29.79,
|
| 682 |
+
"eval_steps_per_second": 3.73,
|
| 683 |
+
"eval_wer": 0.4367363843445848,
|
| 684 |
+
"step": 9000
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 43.5,
|
| 688 |
+
"learning_rate": 2.8495065789473686e-05,
|
| 689 |
+
"loss": 0.1349,
|
| 690 |
+
"step": 9200
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 43.5,
|
| 694 |
+
"eval_loss": 0.5802015066146851,
|
| 695 |
+
"eval_runtime": 98.625,
|
| 696 |
+
"eval_samples_per_second": 29.881,
|
| 697 |
+
"eval_steps_per_second": 3.741,
|
| 698 |
+
"eval_wer": 0.4337958169393249,
|
| 699 |
+
"step": 9200
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 44.44,
|
| 703 |
+
"learning_rate": 2.6850328947368424e-05,
|
| 704 |
+
"loss": 0.1281,
|
| 705 |
+
"step": 9400
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 44.44,
|
| 709 |
+
"eval_loss": 0.6156647205352783,
|
| 710 |
+
"eval_runtime": 98.9856,
|
| 711 |
+
"eval_samples_per_second": 29.772,
|
| 712 |
+
"eval_steps_per_second": 3.728,
|
| 713 |
+
"eval_wer": 0.43706771588320564,
|
| 714 |
+
"step": 9400
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 45.39,
|
| 718 |
+
"learning_rate": 2.520559210526316e-05,
|
| 719 |
+
"loss": 0.1301,
|
| 720 |
+
"step": 9600
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 45.39,
|
| 724 |
+
"eval_loss": 0.6005872488021851,
|
| 725 |
+
"eval_runtime": 98.6022,
|
| 726 |
+
"eval_samples_per_second": 29.888,
|
| 727 |
+
"eval_steps_per_second": 3.742,
|
| 728 |
+
"eval_wer": 0.43122799751501345,
|
| 729 |
+
"step": 9600
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 46.34,
|
| 733 |
+
"learning_rate": 2.3560855263157897e-05,
|
| 734 |
+
"loss": 0.127,
|
| 735 |
+
"step": 9800
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 46.34,
|
| 739 |
+
"eval_loss": 0.5937264561653137,
|
| 740 |
+
"eval_runtime": 98.389,
|
| 741 |
+
"eval_samples_per_second": 29.953,
|
| 742 |
+
"eval_steps_per_second": 3.75,
|
| 743 |
+
"eval_wer": 0.432429074342514,
|
| 744 |
+
"step": 9800
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 47.28,
|
| 748 |
+
"learning_rate": 2.1916118421052635e-05,
|
| 749 |
+
"loss": 0.134,
|
| 750 |
+
"step": 10000
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 47.28,
|
| 754 |
+
"eval_loss": 0.5867904424667358,
|
| 755 |
+
"eval_runtime": 98.4962,
|
| 756 |
+
"eval_samples_per_second": 29.92,
|
| 757 |
+
"eval_steps_per_second": 3.746,
|
| 758 |
+
"eval_wer": 0.43416856492027334,
|
| 759 |
+
"step": 10000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 48.23,
|
| 763 |
+
"learning_rate": 2.0271381578947367e-05,
|
| 764 |
+
"loss": 0.1277,
|
| 765 |
+
"step": 10200
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 48.23,
|
| 769 |
+
"eval_loss": 0.5865517258644104,
|
| 770 |
+
"eval_runtime": 98.5691,
|
| 771 |
+
"eval_samples_per_second": 29.898,
|
| 772 |
+
"eval_steps_per_second": 3.744,
|
| 773 |
+
"eval_wer": 0.4337958169393249,
|
| 774 |
+
"step": 10200
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 49.17,
|
| 778 |
+
"learning_rate": 1.8626644736842105e-05,
|
| 779 |
+
"loss": 0.1229,
|
| 780 |
+
"step": 10400
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 49.17,
|
| 784 |
+
"eval_loss": 0.6024904251098633,
|
| 785 |
+
"eval_runtime": 99.0412,
|
| 786 |
+
"eval_samples_per_second": 29.755,
|
| 787 |
+
"eval_steps_per_second": 3.726,
|
| 788 |
+
"eval_wer": 0.4347483951128598,
|
| 789 |
+
"step": 10400
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 50.12,
|
| 793 |
+
"learning_rate": 1.6981907894736843e-05,
|
| 794 |
+
"loss": 0.127,
|
| 795 |
+
"step": 10600
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 50.12,
|
| 799 |
+
"eval_loss": 0.6073756217956543,
|
| 800 |
+
"eval_runtime": 98.6531,
|
| 801 |
+
"eval_samples_per_second": 29.872,
|
| 802 |
+
"eval_steps_per_second": 3.74,
|
| 803 |
+
"eval_wer": 0.4332574031890661,
|
| 804 |
+
"step": 10600
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 51.06,
|
| 808 |
+
"learning_rate": 1.5337171052631578e-05,
|
| 809 |
+
"loss": 0.1208,
|
| 810 |
+
"step": 10800
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 51.06,
|
| 814 |
+
"eval_loss": 0.5911235809326172,
|
| 815 |
+
"eval_runtime": 98.9125,
|
| 816 |
+
"eval_samples_per_second": 29.794,
|
| 817 |
+
"eval_steps_per_second": 3.731,
|
| 818 |
+
"eval_wer": 0.43081383309173743,
|
| 819 |
+
"step": 10800
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 52.01,
|
| 823 |
+
"learning_rate": 1.3692434210526316e-05,
|
| 824 |
+
"loss": 0.1198,
|
| 825 |
+
"step": 11000
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 52.01,
|
| 829 |
+
"eval_loss": 0.5970575213432312,
|
| 830 |
+
"eval_runtime": 98.4395,
|
| 831 |
+
"eval_samples_per_second": 29.937,
|
| 832 |
+
"eval_steps_per_second": 3.748,
|
| 833 |
+
"eval_wer": 0.42700352039759787,
|
| 834 |
+
"step": 11000
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 52.96,
|
| 838 |
+
"learning_rate": 1.2047697368421053e-05,
|
| 839 |
+
"loss": 0.1164,
|
| 840 |
+
"step": 11200
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 52.96,
|
| 844 |
+
"eval_loss": 0.5997304916381836,
|
| 845 |
+
"eval_runtime": 98.2241,
|
| 846 |
+
"eval_samples_per_second": 30.003,
|
| 847 |
+
"eval_steps_per_second": 3.757,
|
| 848 |
+
"eval_wer": 0.4294885069372541,
|
| 849 |
+
"step": 11200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 53.9,
|
| 853 |
+
"learning_rate": 1.040296052631579e-05,
|
| 854 |
+
"loss": 0.1169,
|
| 855 |
+
"step": 11400
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 53.9,
|
| 859 |
+
"eval_loss": 0.5975005626678467,
|
| 860 |
+
"eval_runtime": 99.0735,
|
| 861 |
+
"eval_samples_per_second": 29.746,
|
| 862 |
+
"eval_steps_per_second": 3.725,
|
| 863 |
+
"eval_wer": 0.4315179126113067,
|
| 864 |
+
"step": 11400
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 54.85,
|
| 868 |
+
"learning_rate": 8.758223684210528e-06,
|
| 869 |
+
"loss": 0.1153,
|
| 870 |
+
"step": 11600
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 54.85,
|
| 874 |
+
"eval_loss": 0.5941161513328552,
|
| 875 |
+
"eval_runtime": 98.5335,
|
| 876 |
+
"eval_samples_per_second": 29.909,
|
| 877 |
+
"eval_steps_per_second": 3.745,
|
| 878 |
+
"eval_wer": 0.42870159453302964,
|
| 879 |
+
"step": 11600
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 55.79,
|
| 883 |
+
"learning_rate": 7.113486842105263e-06,
|
| 884 |
+
"loss": 0.1114,
|
| 885 |
+
"step": 11800
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 55.79,
|
| 889 |
+
"eval_loss": 0.6075084209442139,
|
| 890 |
+
"eval_runtime": 98.2774,
|
| 891 |
+
"eval_samples_per_second": 29.987,
|
| 892 |
+
"eval_steps_per_second": 3.755,
|
| 893 |
+
"eval_wer": 0.4307310002070822,
|
| 894 |
+
"step": 11800
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 56.74,
|
| 898 |
+
"learning_rate": 5.46875e-06,
|
| 899 |
+
"loss": 0.122,
|
| 900 |
+
"step": 12000
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 56.74,
|
| 904 |
+
"eval_loss": 0.6036771535873413,
|
| 905 |
+
"eval_runtime": 98.3003,
|
| 906 |
+
"eval_samples_per_second": 29.98,
|
| 907 |
+
"eval_steps_per_second": 3.754,
|
| 908 |
+
"eval_wer": 0.428453095879064,
|
| 909 |
+
"step": 12000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 57.68,
|
| 913 |
+
"learning_rate": 3.8240131578947365e-06,
|
| 914 |
+
"loss": 0.1099,
|
| 915 |
+
"step": 12200
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 57.68,
|
| 919 |
+
"eval_loss": 0.6065577864646912,
|
| 920 |
+
"eval_runtime": 99.008,
|
| 921 |
+
"eval_samples_per_second": 29.765,
|
| 922 |
+
"eval_steps_per_second": 3.727,
|
| 923 |
+
"eval_wer": 0.42820459722509835,
|
| 924 |
+
"step": 12200
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 58.63,
|
| 928 |
+
"learning_rate": 2.1792763157894734e-06,
|
| 929 |
+
"loss": 0.1151,
|
| 930 |
+
"step": 12400
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 58.63,
|
| 934 |
+
"eval_loss": 0.6106641292572021,
|
| 935 |
+
"eval_runtime": 98.7395,
|
| 936 |
+
"eval_samples_per_second": 29.846,
|
| 937 |
+
"eval_steps_per_second": 3.737,
|
| 938 |
+
"eval_wer": 0.429074342513978,
|
| 939 |
+
"step": 12400
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 59.57,
|
| 943 |
+
"learning_rate": 5.345394736842105e-07,
|
| 944 |
+
"loss": 0.1091,
|
| 945 |
+
"step": 12600
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 59.57,
|
| 949 |
+
"eval_loss": 0.6096903085708618,
|
| 950 |
+
"eval_runtime": 99.3597,
|
| 951 |
+
"eval_samples_per_second": 29.66,
|
| 952 |
+
"eval_steps_per_second": 3.714,
|
| 953 |
+
"eval_wer": 0.42799751501346034,
|
| 954 |
+
"step": 12600
|
| 955 |
+
}
|
| 956 |
+
],
|
| 957 |
+
"logging_steps": 200,
|
| 958 |
+
"max_steps": 12660,
|
| 959 |
+
"num_train_epochs": 60,
|
| 960 |
+
"save_steps": 200,
|
| 961 |
+
"total_flos": 5.409308117842062e+19,
|
| 962 |
+
"trial_name": null,
|
| 963 |
+
"trial_params": null
|
| 964 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2d1ace70e72eaa41fa4a0667c04bd2c5ba46a65dcee9d04ae3bcbd692832b3e
|
| 3 |
+
size 4472
|