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.1675227901.e18ab16fa5fa.6769.0 +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 sha256:443ffa8aa7357e63f5ac345b550587f55b1219b2414d37f8e79c22bccb49dbb6
|
| 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 sha256:38ca7d8f211eeadc90dd89e19a1d050c57bea6c91ef1fab62f496eb5df5d955e
|
| 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:ffd63620c7b98446eef7bae7a938362e2b36d7c505fedc94471fced9fed2e53b
|
| 3 |
+
size 14639
|
checkpoint-9000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e610997d991a27295700f218bb6e249c1b3761412db7085605094e2dfd6097be
|
| 3 |
+
size 557
|
checkpoint-9000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7e77456376411a061885c58683b3c5ef476a59291e897d4a875cf19aad42087
|
| 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": 6.731488406881077,
|
| 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": 2.0000000000000002e-07,
|
| 13 |
+
"loss": 18.6192,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.37,
|
| 18 |
+
"learning_rate": 9.94e-05,
|
| 19 |
+
"loss": 7.5397,
|
| 20 |
+
"step": 500
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.37,
|
| 24 |
+
"eval_cer": 0.9810978889654326,
|
| 25 |
+
"eval_clean_cer": 0.9774387393628106,
|
| 26 |
+
"eval_loss": 3.571558952331543,
|
| 27 |
+
"eval_runtime": 221.4433,
|
| 28 |
+
"eval_samples_per_second": 24.679,
|
| 29 |
+
"eval_steps_per_second": 1.544,
|
| 30 |
+
"eval_wer": 1.0,
|
| 31 |
+
"learning_rate": 9.94e-05,
|
| 32 |
+
"step": 500
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.75,
|
| 36 |
+
"learning_rate": 9.613830613830615e-05,
|
| 37 |
+
"loss": 1.7478,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.75,
|
| 42 |
+
"eval_cer": 0.22960449951399964,
|
| 43 |
+
"eval_clean_cer": 0.17457099250398456,
|
| 44 |
+
"eval_loss": 0.7702281475067139,
|
| 45 |
+
"eval_runtime": 224.0929,
|
| 46 |
+
"eval_samples_per_second": 24.387,
|
| 47 |
+
"eval_steps_per_second": 1.526,
|
| 48 |
+
"eval_wer": 0.8097043024248205,
|
| 49 |
+
"learning_rate": 9.613830613830615e-05,
|
| 50 |
+
"step": 1000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.12,
|
| 54 |
+
"learning_rate": 9.225330225330226e-05,
|
| 55 |
+
"loss": 0.7687,
|
| 56 |
+
"step": 1500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.12,
|
| 60 |
+
"eval_cer": 0.14148744420432777,
|
| 61 |
+
"eval_clean_cer": 0.11820726398251868,
|
| 62 |
+
"eval_loss": 0.4996742308139801,
|
| 63 |
+
"eval_runtime": 221.7353,
|
| 64 |
+
"eval_samples_per_second": 24.647,
|
| 65 |
+
"eval_steps_per_second": 1.542,
|
| 66 |
+
"eval_wer": 0.5391836939605402,
|
| 67 |
+
"learning_rate": 9.225330225330226e-05,
|
| 68 |
+
"step": 1500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.5,
|
| 72 |
+
"learning_rate": 8.836829836829838e-05,
|
| 73 |
+
"loss": 0.6064,
|
| 74 |
+
"step": 2000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.5,
|
| 78 |
+
"eval_cer": 0.12378853794105713,
|
| 79 |
+
"eval_clean_cer": 0.10011770602778763,
|
| 80 |
+
"eval_loss": 0.4269550144672394,
|
| 81 |
+
"eval_runtime": 224.0891,
|
| 82 |
+
"eval_samples_per_second": 24.388,
|
| 83 |
+
"eval_steps_per_second": 1.526,
|
| 84 |
+
"eval_wer": 0.49563231085897885,
|
| 85 |
+
"learning_rate": 8.836829836829838e-05,
|
| 86 |
+
"step": 2000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.87,
|
| 90 |
+
"learning_rate": 8.448329448329449e-05,
|
| 91 |
+
"loss": 0.5473,
|
| 92 |
+
"step": 2500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.87,
|
| 96 |
+
"eval_cer": 0.1105108194060415,
|
| 97 |
+
"eval_clean_cer": 0.0898226524968884,
|
| 98 |
+
"eval_loss": 0.38087567687034607,
|
| 99 |
+
"eval_runtime": 223.664,
|
| 100 |
+
"eval_samples_per_second": 24.434,
|
| 101 |
+
"eval_steps_per_second": 1.529,
|
| 102 |
+
"eval_wer": 0.4489432200411667,
|
| 103 |
+
"learning_rate": 8.448329448329449e-05,
|
| 104 |
+
"step": 2500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.24,
|
| 108 |
+
"learning_rate": 8.05982905982906e-05,
|
| 109 |
+
"loss": 0.454,
|
| 110 |
+
"step": 3000
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.24,
|
| 114 |
+
"eval_cer": 0.10214972585805014,
|
| 115 |
+
"eval_clean_cer": 0.08129037344912453,
|
| 116 |
+
"eval_loss": 0.3585045337677002,
|
| 117 |
+
"eval_runtime": 225.448,
|
| 118 |
+
"eval_samples_per_second": 24.241,
|
| 119 |
+
"eval_steps_per_second": 1.517,
|
| 120 |
+
"eval_wer": 0.4256237762939907,
|
| 121 |
+
"learning_rate": 8.05982905982906e-05,
|
| 122 |
+
"step": 3000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.62,
|
| 126 |
+
"learning_rate": 7.671328671328672e-05,
|
| 127 |
+
"loss": 0.4219,
|
| 128 |
+
"step": 3500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.62,
|
| 132 |
+
"eval_cer": 0.0973510621231138,
|
| 133 |
+
"eval_clean_cer": 0.07773103327870422,
|
| 134 |
+
"eval_loss": 0.3375051021575928,
|
| 135 |
+
"eval_runtime": 226.653,
|
| 136 |
+
"eval_samples_per_second": 24.112,
|
| 137 |
+
"eval_steps_per_second": 1.509,
|
| 138 |
+
"eval_wer": 0.40634570008534565,
|
| 139 |
+
"learning_rate": 7.671328671328672e-05,
|
| 140 |
+
"step": 3500
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.99,
|
| 144 |
+
"learning_rate": 7.282828282828284e-05,
|
| 145 |
+
"loss": 0.4075,
|
| 146 |
+
"step": 4000
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.99,
|
| 150 |
+
"eval_cer": 0.09484084667868299,
|
| 151 |
+
"eval_clean_cer": 0.07456029195600385,
|
| 152 |
+
"eval_loss": 0.3274226784706116,
|
| 153 |
+
"eval_runtime": 225.9771,
|
| 154 |
+
"eval_samples_per_second": 24.184,
|
| 155 |
+
"eval_steps_per_second": 1.513,
|
| 156 |
+
"eval_wer": 0.4035845172950449,
|
| 157 |
+
"learning_rate": 7.282828282828284e-05,
|
| 158 |
+
"step": 4000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.37,
|
| 162 |
+
"learning_rate": 6.894327894327895e-05,
|
| 163 |
+
"loss": 0.3355,
|
| 164 |
+
"step": 4500
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 3.37,
|
| 168 |
+
"eval_cer": 0.08976851283890268,
|
| 169 |
+
"eval_clean_cer": 0.07285946801380934,
|
| 170 |
+
"eval_loss": 0.3256622850894928,
|
| 171 |
+
"eval_runtime": 227.1344,
|
| 172 |
+
"eval_samples_per_second": 24.061,
|
| 173 |
+
"eval_steps_per_second": 1.506,
|
| 174 |
+
"eval_wer": 0.3781816356242783,
|
| 175 |
+
"learning_rate": 6.894327894327895e-05,
|
| 176 |
+
"step": 4500
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.74,
|
| 180 |
+
"learning_rate": 6.506604506604507e-05,
|
| 181 |
+
"loss": 0.3203,
|
| 182 |
+
"step": 5000
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 3.74,
|
| 186 |
+
"eval_cer": 0.08301169231930695,
|
| 187 |
+
"eval_clean_cer": 0.06594916676522435,
|
| 188 |
+
"eval_loss": 0.30244797468185425,
|
| 189 |
+
"eval_runtime": 226.4786,
|
| 190 |
+
"eval_samples_per_second": 24.13,
|
| 191 |
+
"eval_steps_per_second": 1.51,
|
| 192 |
+
"eval_wer": 0.35606707164014256,
|
| 193 |
+
"learning_rate": 6.506604506604507e-05,
|
| 194 |
+
"step": 5000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 4.11,
|
| 198 |
+
"learning_rate": 6.118104118104118e-05,
|
| 199 |
+
"loss": 0.3151,
|
| 200 |
+
"step": 5500
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 4.11,
|
| 204 |
+
"eval_cer": 0.08304472146989157,
|
| 205 |
+
"eval_clean_cer": 0.06525081521280011,
|
| 206 |
+
"eval_loss": 0.3038225769996643,
|
| 207 |
+
"eval_runtime": 228.8025,
|
| 208 |
+
"eval_samples_per_second": 23.885,
|
| 209 |
+
"eval_steps_per_second": 1.495,
|
| 210 |
+
"eval_wer": 0.36061047241327376,
|
| 211 |
+
"learning_rate": 6.118104118104118e-05,
|
| 212 |
+
"step": 5500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.49,
|
| 216 |
+
"learning_rate": 5.72960372960373e-05,
|
| 217 |
+
"loss": 0.2713,
|
| 218 |
+
"step": 6000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 4.49,
|
| 222 |
+
"eval_cer": 0.08317211962214652,
|
| 223 |
+
"eval_clean_cer": 0.06550424924392181,
|
| 224 |
+
"eval_loss": 0.30516648292541504,
|
| 225 |
+
"eval_runtime": 228.6779,
|
| 226 |
+
"eval_samples_per_second": 23.898,
|
| 227 |
+
"eval_steps_per_second": 1.496,
|
| 228 |
+
"eval_wer": 0.3594557959736935,
|
| 229 |
+
"learning_rate": 5.72960372960373e-05,
|
| 230 |
+
"step": 6000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 4.86,
|
| 234 |
+
"learning_rate": 5.3411033411033415e-05,
|
| 235 |
+
"loss": 0.2685,
|
| 236 |
+
"step": 6500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 4.86,
|
| 240 |
+
"eval_cer": 0.07956250530825634,
|
| 241 |
+
"eval_clean_cer": 0.06275026610573267,
|
| 242 |
+
"eval_loss": 0.29325252771377563,
|
| 243 |
+
"eval_runtime": 228.92,
|
| 244 |
+
"eval_samples_per_second": 23.873,
|
| 245 |
+
"eval_steps_per_second": 1.494,
|
| 246 |
+
"eval_wer": 0.34364174908378936,
|
| 247 |
+
"learning_rate": 5.3411033411033415e-05,
|
| 248 |
+
"step": 6500
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 5.24,
|
| 252 |
+
"learning_rate": 4.952602952602953e-05,
|
| 253 |
+
"loss": 0.2379,
|
| 254 |
+
"step": 7000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 5.24,
|
| 258 |
+
"eval_cer": 0.07627846405012881,
|
| 259 |
+
"eval_clean_cer": 0.060807271867132986,
|
| 260 |
+
"eval_loss": 0.30203360319137573,
|
| 261 |
+
"eval_runtime": 229.4624,
|
| 262 |
+
"eval_samples_per_second": 23.817,
|
| 263 |
+
"eval_steps_per_second": 1.49,
|
| 264 |
+
"eval_wer": 0.3361614538882474,
|
| 265 |
+
"learning_rate": 4.952602952602953e-05,
|
| 266 |
+
"step": 7000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 5.61,
|
| 270 |
+
"learning_rate": 4.564879564879565e-05,
|
| 271 |
+
"loss": 0.224,
|
| 272 |
+
"step": 7500
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 5.61,
|
| 276 |
+
"eval_cer": 0.07449960836864307,
|
| 277 |
+
"eval_clean_cer": 0.058937491904190675,
|
| 278 |
+
"eval_loss": 0.2874354124069214,
|
| 279 |
+
"eval_runtime": 229.9772,
|
| 280 |
+
"eval_samples_per_second": 23.763,
|
| 281 |
+
"eval_steps_per_second": 1.487,
|
| 282 |
+
"eval_wer": 0.3264973141221949,
|
| 283 |
+
"learning_rate": 4.564879564879565e-05,
|
| 284 |
+
"step": 7500
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 5.98,
|
| 288 |
+
"learning_rate": 4.1763791763791764e-05,
|
| 289 |
+
"loss": 0.2204,
|
| 290 |
+
"step": 8000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 5.98,
|
| 294 |
+
"eval_cer": 0.07241877188181227,
|
| 295 |
+
"eval_clean_cer": 0.05759147560556654,
|
| 296 |
+
"eval_loss": 0.29218629002571106,
|
| 297 |
+
"eval_runtime": 229.2706,
|
| 298 |
+
"eval_samples_per_second": 23.836,
|
| 299 |
+
"eval_steps_per_second": 1.492,
|
| 300 |
+
"eval_wer": 0.31909232391184295,
|
| 301 |
+
"learning_rate": 4.1763791763791764e-05,
|
| 302 |
+
"step": 8000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 6.36,
|
| 306 |
+
"learning_rate": 3.787878787878788e-05,
|
| 307 |
+
"loss": 0.1927,
|
| 308 |
+
"step": 8500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 6.36,
|
| 312 |
+
"eval_cer": 0.0719469268734606,
|
| 313 |
+
"eval_clean_cer": 0.05684243724691796,
|
| 314 |
+
"eval_loss": 0.3106653392314911,
|
| 315 |
+
"eval_runtime": 228.9966,
|
| 316 |
+
"eval_samples_per_second": 23.865,
|
| 317 |
+
"eval_steps_per_second": 1.493,
|
| 318 |
+
"eval_wer": 0.3163060394598122,
|
| 319 |
+
"learning_rate": 3.787878787878788e-05,
|
| 320 |
+
"step": 8500
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 6.73,
|
| 324 |
+
"learning_rate": 3.3993783993783994e-05,
|
| 325 |
+
"loss": 0.1875,
|
| 326 |
+
"step": 9000
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 6.73,
|
| 330 |
+
"eval_cer": 0.07033793539498145,
|
| 331 |
+
"eval_clean_cer": 0.05535562426433733,
|
| 332 |
+
"eval_loss": 0.30340105295181274,
|
| 333 |
+
"eval_runtime": 229.2234,
|
| 334 |
+
"eval_samples_per_second": 23.841,
|
| 335 |
+
"eval_steps_per_second": 1.492,
|
| 336 |
+
"eval_wer": 0.30837391435313016,
|
| 337 |
+
"learning_rate": 3.3993783993783994e-05,
|
| 338 |
+
"step": 9000
|
| 339 |
+
}
|
| 340 |
+
],
|
| 341 |
+
"max_steps": 13370,
|
| 342 |
+
"num_train_epochs": 10,
|
| 343 |
+
"total_flos": 3.801067969752696e+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:c3f3a910c1fa3764f791b92e4fbd049f783da4b790e4aa694797f8b523e19b24
|
| 3 |
+
size 3515
|
logs/events.out.tfevents.1675227901.e18ab16fa5fa.6769.0
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:a18ddae6f1439fae5f9c44f5736c4676b0b298e2a57e493fa586877f8e7b397c
|
| 3 |
+
size 16845
|
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 sha256:38ca7d8f211eeadc90dd89e19a1d050c57bea6c91ef1fab62f496eb5df5d955e
|
| 3 |
size 1262184749
|