Training in progress, step 9000
Browse files- checkpoint-9000/config.json +108 -0
- checkpoint-9000/optimizer.pt +3 -0
- checkpoint-9000/preprocessor_config.json +9 -0
- checkpoint-9000/pytorch_model.bin +3 -0
- checkpoint-9000/rng_state.pth +3 -0
- checkpoint-9000/scaler.pt +3 -0
- checkpoint-9000/scheduler.pt +3 -0
- checkpoint-9000/trainer_state.json +346 -0
- checkpoint-9000/training_args.bin +3 -0
- logs/events.out.tfevents.1675161831.31efd5474bec.3677.0 +2 -2
- pytorch_model.bin +1 -1
checkpoint-9000/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": 66,
|
| 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": "4.27.0.dev0",
|
| 105 |
+
"use_weighted_layer_sum": false,
|
| 106 |
+
"vocab_size": 69,
|
| 107 |
+
"xvector_output_dim": 512
|
| 108 |
+
}
|
checkpoint-9000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64552e1195fcd890b39498f2e3e4455e4ec72317e62e9cd1cacc94e6b33a7057
|
| 3 |
+
size 2490626757
|
checkpoint-9000/preprocessor_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0.0,
|
| 7 |
+
"return_attention_mask": true,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|
checkpoint-9000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18426538947e52da3c1e8f27c815ca724a1df520cb0c6a17d891480001b67fdb
|
| 3 |
+
size 1262184749
|
checkpoint-9000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5dde79af8d59b38cb8d3428b162aee6f752e7d61a9ea497f0637643d311b1fbe
|
| 3 |
+
size 14639
|
checkpoint-9000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18a5ac19cf9a59e36d0685d9a0d5d0485a0a28f52afb743639b071adc9d0afac
|
| 3 |
+
size 557
|
checkpoint-9000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bdb5ed47903d0c389a071f7d8ef576b8a15f78fc7ced5dfc4ca7f11d9d83cf45
|
| 3 |
+
size 627
|
checkpoint-9000/trainer_state.json
ADDED
|
@@ -0,0 +1,346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 7.228915662650603,
|
| 5 |
+
"global_step": 9000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 0.0,
|
| 13 |
+
"loss": 36.5036,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.4,
|
| 18 |
+
"learning_rate": 4.96e-05,
|
| 19 |
+
"loss": 8.5484,
|
| 20 |
+
"step": 500
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.4,
|
| 24 |
+
"eval_cer": 1.0,
|
| 25 |
+
"eval_clean_cer": 1.0,
|
| 26 |
+
"eval_loss": 3.6234467029571533,
|
| 27 |
+
"eval_runtime": 384.6662,
|
| 28 |
+
"eval_samples_per_second": 19.9,
|
| 29 |
+
"eval_steps_per_second": 1.245,
|
| 30 |
+
"eval_wer": 1.0,
|
| 31 |
+
"learning_rate": 4.96e-05,
|
| 32 |
+
"step": 500
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.8,
|
| 36 |
+
"learning_rate": 4.792887029288703e-05,
|
| 37 |
+
"loss": 3.2275,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.8,
|
| 42 |
+
"eval_cer": 0.7080718890168877,
|
| 43 |
+
"eval_clean_cer": 0.653960461430081,
|
| 44 |
+
"eval_loss": 2.2960469722747803,
|
| 45 |
+
"eval_runtime": 383.0083,
|
| 46 |
+
"eval_samples_per_second": 19.987,
|
| 47 |
+
"eval_steps_per_second": 1.251,
|
| 48 |
+
"eval_wer": 0.9997886281969985,
|
| 49 |
+
"learning_rate": 4.792887029288703e-05,
|
| 50 |
+
"step": 1000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.2,
|
| 54 |
+
"learning_rate": 4.5841004184100424e-05,
|
| 55 |
+
"loss": 0.9955,
|
| 56 |
+
"step": 1500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.2,
|
| 60 |
+
"eval_cer": 0.43273425819260275,
|
| 61 |
+
"eval_clean_cer": 0.37557605377480335,
|
| 62 |
+
"eval_loss": 1.2224403619766235,
|
| 63 |
+
"eval_runtime": 382.1035,
|
| 64 |
+
"eval_samples_per_second": 20.034,
|
| 65 |
+
"eval_steps_per_second": 1.254,
|
| 66 |
+
"eval_wer": 0.9549127684828382,
|
| 67 |
+
"learning_rate": 4.5841004184100424e-05,
|
| 68 |
+
"step": 1500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.61,
|
| 72 |
+
"learning_rate": 4.37489539748954e-05,
|
| 73 |
+
"loss": 0.66,
|
| 74 |
+
"step": 2000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.61,
|
| 78 |
+
"eval_cer": 0.36509166891345374,
|
| 79 |
+
"eval_clean_cer": 0.304027973464835,
|
| 80 |
+
"eval_loss": 0.9558963775634766,
|
| 81 |
+
"eval_runtime": 380.573,
|
| 82 |
+
"eval_samples_per_second": 20.114,
|
| 83 |
+
"eval_steps_per_second": 1.259,
|
| 84 |
+
"eval_wer": 0.9231907386631546,
|
| 85 |
+
"learning_rate": 4.37489539748954e-05,
|
| 86 |
+
"step": 2000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.01,
|
| 90 |
+
"learning_rate": 4.1665271966527195e-05,
|
| 91 |
+
"loss": 0.546,
|
| 92 |
+
"step": 2500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.01,
|
| 96 |
+
"eval_cer": 0.3585320718645065,
|
| 97 |
+
"eval_clean_cer": 0.2825745567688153,
|
| 98 |
+
"eval_loss": 0.920676589012146,
|
| 99 |
+
"eval_runtime": 379.317,
|
| 100 |
+
"eval_samples_per_second": 20.181,
|
| 101 |
+
"eval_steps_per_second": 1.263,
|
| 102 |
+
"eval_wer": 0.948051314570021,
|
| 103 |
+
"learning_rate": 4.1665271966527195e-05,
|
| 104 |
+
"step": 2500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.41,
|
| 108 |
+
"learning_rate": 3.957740585774059e-05,
|
| 109 |
+
"loss": 0.4459,
|
| 110 |
+
"step": 3000
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.41,
|
| 114 |
+
"eval_cer": 0.29398698497512193,
|
| 115 |
+
"eval_clean_cer": 0.23832115181401903,
|
| 116 |
+
"eval_loss": 0.7700594067573547,
|
| 117 |
+
"eval_runtime": 382.0036,
|
| 118 |
+
"eval_samples_per_second": 20.039,
|
| 119 |
+
"eval_steps_per_second": 1.254,
|
| 120 |
+
"eval_wer": 0.869307188267239,
|
| 121 |
+
"learning_rate": 3.957740585774059e-05,
|
| 122 |
+
"step": 3000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.81,
|
| 126 |
+
"learning_rate": 3.748953974895398e-05,
|
| 127 |
+
"loss": 0.4041,
|
| 128 |
+
"step": 3500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.81,
|
| 132 |
+
"eval_cer": 0.2948846785460428,
|
| 133 |
+
"eval_clean_cer": 0.26338499471644944,
|
| 134 |
+
"eval_loss": 0.7755610346794128,
|
| 135 |
+
"eval_runtime": 382.5716,
|
| 136 |
+
"eval_samples_per_second": 20.009,
|
| 137 |
+
"eval_steps_per_second": 1.252,
|
| 138 |
+
"eval_wer": 0.8223663886314488,
|
| 139 |
+
"learning_rate": 3.748953974895398e-05,
|
| 140 |
+
"step": 3500
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 3.21,
|
| 144 |
+
"learning_rate": 3.5397489539748955e-05,
|
| 145 |
+
"loss": 0.3637,
|
| 146 |
+
"step": 4000
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 3.21,
|
| 150 |
+
"eval_cer": 0.20644807470771342,
|
| 151 |
+
"eval_clean_cer": 0.18069009040742046,
|
| 152 |
+
"eval_loss": 0.6014806032180786,
|
| 153 |
+
"eval_runtime": 383.3843,
|
| 154 |
+
"eval_samples_per_second": 19.967,
|
| 155 |
+
"eval_steps_per_second": 1.249,
|
| 156 |
+
"eval_wer": 0.7014942360535259,
|
| 157 |
+
"learning_rate": 3.5397489539748955e-05,
|
| 158 |
+
"step": 4000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.61,
|
| 162 |
+
"learning_rate": 3.330962343096235e-05,
|
| 163 |
+
"loss": 0.334,
|
| 164 |
+
"step": 4500
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 3.61,
|
| 168 |
+
"eval_cer": 0.19067869310522317,
|
| 169 |
+
"eval_clean_cer": 0.1638084125865915,
|
| 170 |
+
"eval_loss": 0.5615196228027344,
|
| 171 |
+
"eval_runtime": 378.29,
|
| 172 |
+
"eval_samples_per_second": 20.236,
|
| 173 |
+
"eval_steps_per_second": 1.266,
|
| 174 |
+
"eval_wer": 0.667495894509211,
|
| 175 |
+
"learning_rate": 3.330962343096235e-05,
|
| 176 |
+
"step": 4500
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 4.02,
|
| 180 |
+
"learning_rate": 3.1225941422594144e-05,
|
| 181 |
+
"loss": 0.3283,
|
| 182 |
+
"step": 5000
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 4.02,
|
| 186 |
+
"eval_cer": 0.20923613323855977,
|
| 187 |
+
"eval_clean_cer": 0.18034519196900317,
|
| 188 |
+
"eval_loss": 0.6205064058303833,
|
| 189 |
+
"eval_runtime": 383.8788,
|
| 190 |
+
"eval_samples_per_second": 19.941,
|
| 191 |
+
"eval_steps_per_second": 1.248,
|
| 192 |
+
"eval_wer": 0.707282571581874,
|
| 193 |
+
"learning_rate": 3.1225941422594144e-05,
|
| 194 |
+
"step": 5000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.42,
|
| 198 |
+
"learning_rate": 2.914644351464435e-05,
|
| 199 |
+
"loss": 0.3762,
|
| 200 |
+
"step": 5500
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 4.42,
|
| 204 |
+
"eval_cer": 0.1777892840510797,
|
| 205 |
+
"eval_clean_cer": 0.1600145297640014,
|
| 206 |
+
"eval_loss": 0.7516510486602783,
|
| 207 |
+
"eval_runtime": 383.1576,
|
| 208 |
+
"eval_samples_per_second": 19.979,
|
| 209 |
+
"eval_steps_per_second": 1.25,
|
| 210 |
+
"eval_wer": 0.63658683316261,
|
| 211 |
+
"learning_rate": 2.914644351464435e-05,
|
| 212 |
+
"step": 5500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.82,
|
| 216 |
+
"learning_rate": 2.705439330543933e-05,
|
| 217 |
+
"loss": 0.4954,
|
| 218 |
+
"step": 6000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 4.82,
|
| 222 |
+
"eval_cer": 0.2023119439201941,
|
| 223 |
+
"eval_clean_cer": 0.1735132675824821,
|
| 224 |
+
"eval_loss": 0.937389612197876,
|
| 225 |
+
"eval_runtime": 379.9047,
|
| 226 |
+
"eval_samples_per_second": 20.15,
|
| 227 |
+
"eval_steps_per_second": 1.261,
|
| 228 |
+
"eval_wer": 0.7072988309513357,
|
| 229 |
+
"learning_rate": 2.705439330543933e-05,
|
| 230 |
+
"step": 6000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 5.22,
|
| 234 |
+
"learning_rate": 2.496234309623431e-05,
|
| 235 |
+
"loss": 0.5568,
|
| 236 |
+
"step": 6500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 5.22,
|
| 240 |
+
"eval_cer": 0.19821564254025834,
|
| 241 |
+
"eval_clean_cer": 0.16663731360807796,
|
| 242 |
+
"eval_loss": 0.8858793377876282,
|
| 243 |
+
"eval_runtime": 379.7569,
|
| 244 |
+
"eval_samples_per_second": 20.158,
|
| 245 |
+
"eval_steps_per_second": 1.261,
|
| 246 |
+
"eval_wer": 0.7027462075020731,
|
| 247 |
+
"learning_rate": 2.496234309623431e-05,
|
| 248 |
+
"step": 6500
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 5.62,
|
| 252 |
+
"learning_rate": 2.28744769874477e-05,
|
| 253 |
+
"loss": 0.6756,
|
| 254 |
+
"step": 7000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 5.62,
|
| 258 |
+
"eval_cer": 0.19202370156131277,
|
| 259 |
+
"eval_clean_cer": 0.16278105553598685,
|
| 260 |
+
"eval_loss": 1.0252363681793213,
|
| 261 |
+
"eval_runtime": 381.5363,
|
| 262 |
+
"eval_samples_per_second": 20.064,
|
| 263 |
+
"eval_steps_per_second": 1.255,
|
| 264 |
+
"eval_wer": 0.6802432401671463,
|
| 265 |
+
"learning_rate": 2.28744769874477e-05,
|
| 266 |
+
"step": 7000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 6.02,
|
| 270 |
+
"learning_rate": 2.0790794979079496e-05,
|
| 271 |
+
"loss": 0.7752,
|
| 272 |
+
"step": 7500
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 6.02,
|
| 276 |
+
"eval_cer": 0.2309217137674943,
|
| 277 |
+
"eval_clean_cer": 0.19081322648820007,
|
| 278 |
+
"eval_loss": 1.12592613697052,
|
| 279 |
+
"eval_runtime": 381.2563,
|
| 280 |
+
"eval_samples_per_second": 20.078,
|
| 281 |
+
"eval_steps_per_second": 1.256,
|
| 282 |
+
"eval_wer": 0.7656537079492057,
|
| 283 |
+
"learning_rate": 2.0790794979079496e-05,
|
| 284 |
+
"step": 7500
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 6.43,
|
| 288 |
+
"learning_rate": 1.87071129707113e-05,
|
| 289 |
+
"loss": 0.8305,
|
| 290 |
+
"step": 8000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 6.43,
|
| 294 |
+
"eval_cer": 0.3252438785264345,
|
| 295 |
+
"eval_clean_cer": 0.26681563343900433,
|
| 296 |
+
"eval_loss": 1.385704517364502,
|
| 297 |
+
"eval_runtime": 381.2294,
|
| 298 |
+
"eval_samples_per_second": 20.08,
|
| 299 |
+
"eval_steps_per_second": 1.256,
|
| 300 |
+
"eval_wer": 0.9028990455750125,
|
| 301 |
+
"learning_rate": 1.87071129707113e-05,
|
| 302 |
+
"step": 8000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 6.83,
|
| 306 |
+
"learning_rate": 1.6619246861924685e-05,
|
| 307 |
+
"loss": 1.7385,
|
| 308 |
+
"step": 8500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 6.83,
|
| 312 |
+
"eval_cer": 0.9234264320203927,
|
| 313 |
+
"eval_clean_cer": 0.911353763062111,
|
| 314 |
+
"eval_loss": 3.2320151329040527,
|
| 315 |
+
"eval_runtime": 377.3136,
|
| 316 |
+
"eval_samples_per_second": 20.288,
|
| 317 |
+
"eval_steps_per_second": 1.27,
|
| 318 |
+
"eval_wer": 0.9998374063053834,
|
| 319 |
+
"learning_rate": 1.6619246861924685e-05,
|
| 320 |
+
"step": 8500
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 7.23,
|
| 324 |
+
"learning_rate": 1.4527196652719665e-05,
|
| 325 |
+
"loss": 2.7839,
|
| 326 |
+
"step": 9000
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 7.23,
|
| 330 |
+
"eval_cer": 0.9399648275693032,
|
| 331 |
+
"eval_clean_cer": 0.9305836855700363,
|
| 332 |
+
"eval_loss": 3.3238463401794434,
|
| 333 |
+
"eval_runtime": 377.6325,
|
| 334 |
+
"eval_samples_per_second": 20.271,
|
| 335 |
+
"eval_steps_per_second": 1.268,
|
| 336 |
+
"eval_wer": 0.9998861844137684,
|
| 337 |
+
"learning_rate": 1.4527196652719665e-05,
|
| 338 |
+
"step": 9000
|
| 339 |
+
}
|
| 340 |
+
],
|
| 341 |
+
"max_steps": 12450,
|
| 342 |
+
"num_train_epochs": 10,
|
| 343 |
+
"total_flos": 9.660949620775597e+19,
|
| 344 |
+
"trial_name": null,
|
| 345 |
+
"trial_params": null
|
| 346 |
+
}
|
checkpoint-9000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5202a12b1552089ddded38ec8212e923965f6e5e5e1bf9a39ed5b7bedc1d608
|
| 3 |
+
size 3515
|
logs/events.out.tfevents.1675161831.31efd5474bec.3677.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f31dccc451ae3a3dc46caf3299bb4d39a649d52ec5da5c96db33d5eedfe8cb24
|
| 3 |
+
size 16783
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262184749
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18426538947e52da3c1e8f27c815ca724a1df520cb0c6a17d891480001b67fdb
|
| 3 |
size 1262184749
|