Commit
•
8c7e4eb
1
Parent(s):
9ee5c5a
initial commit
Browse files- config.json +108 -0
- optimizer.pt +3 -0
- preprocessor_config.json +10 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- runs/Jun19_15-33-48_b74f8961b262/events.out.tfevents.1687189077.b74f8961b262.9962.0 +3 -0
- runs/Jun19_15-40-35_b74f8961b262/events.out.tfevents.1687189481.b74f8961b262.9962.1 +3 -0
- runs/Jun19_16-29-55_0ad83369d0e7/events.out.tfevents.1687192421.0ad83369d0e7.5814.0 +3 -0
- scheduler.pt +3 -0
- trainer_state.json +352 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/mms-1b-all",
|
| 3 |
+
"activation_dropout": 0.05,
|
| 4 |
+
"adapter_attn_dim": 16,
|
| 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": 0.05,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"classifier_proj_size": 256,
|
| 15 |
+
"codevector_dim": 1024,
|
| 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": 0.05,
|
| 54 |
+
"feat_quantizer_dropout": 0.0,
|
| 55 |
+
"final_dropout": 0.05,
|
| 56 |
+
"hidden_act": "gelu",
|
| 57 |
+
"hidden_dropout": 0.05,
|
| 58 |
+
"hidden_size": 1280,
|
| 59 |
+
"initializer_range": 0.02,
|
| 60 |
+
"intermediate_size": 5120,
|
| 61 |
+
"layer_norm_eps": 1e-05,
|
| 62 |
+
"layerdrop": 0.05,
|
| 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": 48,
|
| 78 |
+
"num_negatives": 100,
|
| 79 |
+
"output_hidden_size": 1280,
|
| 80 |
+
"pad_token_id": 0,
|
| 81 |
+
"proj_codevector_dim": 1024,
|
| 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": "4.30.2",
|
| 105 |
+
"use_weighted_layer_sum": false,
|
| 106 |
+
"vocab_size": 65,
|
| 107 |
+
"xvector_output_dim": 512
|
| 108 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48c3f30cca56ba15a27b0863face6e9f118b291eb6ee3e04a6e063c57ed4741b
|
| 3 |
+
size 7684809701
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0,
|
| 7 |
+
"processor_class": "Wav2Vec2Processor",
|
| 8 |
+
"return_attention_mask": true,
|
| 9 |
+
"sampling_rate": 16000
|
| 10 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b1d3c91971a765bbaaa60897f53056eaf07d999354840b8d591a11386d80139
|
| 3 |
+
size 3859308813
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fbae8cbe561e057e544e38ccae9c256ea41a9888d5b3efd3e49b4951a071f452
|
| 3 |
+
size 14639
|
runs/Jun19_15-33-48_b74f8961b262/events.out.tfevents.1687189077.b74f8961b262.9962.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:703ca2705ad867632d172e89f3b5dca5500bbd5a77d15667fec158bc86895fca
|
| 3 |
+
size 5435
|
runs/Jun19_15-40-35_b74f8961b262/events.out.tfevents.1687189481.b74f8961b262.9962.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5b540c739e5aecff034ce2c3d38c42ed25813c7b29aa0b58b3179f253251ace
|
| 3 |
+
size 5435
|
runs/Jun19_16-29-55_0ad83369d0e7/events.out.tfevents.1687192421.0ad83369d0e7.5814.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b3ec1f2f6d40601de3669d78b19cef88206fc539746ca4c8422fdf54b3e6600
|
| 3 |
+
size 17208
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f7a2fe725797468e1522d38ad7abf34b4fb71eedc1b57f3fa2325530227240b
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,352 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 18.823529411764707,
|
| 5 |
+
"global_step": 5600,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.67,
|
| 12 |
+
"eval_loss": 0.8018701076507568,
|
| 13 |
+
"eval_runtime": 123.0686,
|
| 14 |
+
"eval_samples_per_second": 17.892,
|
| 15 |
+
"eval_steps_per_second": 2.243,
|
| 16 |
+
"eval_wer": 0.8813849519642347,
|
| 17 |
+
"step": 200
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.34,
|
| 21 |
+
"learning_rate": 0.0007940000000000001,
|
| 22 |
+
"loss": 1.228,
|
| 23 |
+
"step": 400
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.34,
|
| 27 |
+
"eval_loss": 1.0962814092636108,
|
| 28 |
+
"eval_runtime": 123.3569,
|
| 29 |
+
"eval_samples_per_second": 17.851,
|
| 30 |
+
"eval_steps_per_second": 2.237,
|
| 31 |
+
"eval_wer": 0.9425473223627889,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.02,
|
| 36 |
+
"eval_loss": 1.104669451713562,
|
| 37 |
+
"eval_runtime": 123.8837,
|
| 38 |
+
"eval_samples_per_second": 17.775,
|
| 39 |
+
"eval_steps_per_second": 2.228,
|
| 40 |
+
"eval_wer": 0.9653762008941311,
|
| 41 |
+
"step": 600
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 2.69,
|
| 45 |
+
"learning_rate": 0.0009454044117647059,
|
| 46 |
+
"loss": 0.7814,
|
| 47 |
+
"step": 800
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 2.69,
|
| 51 |
+
"eval_loss": 0.9275535345077515,
|
| 52 |
+
"eval_runtime": 124.6162,
|
| 53 |
+
"eval_samples_per_second": 17.67,
|
| 54 |
+
"eval_steps_per_second": 2.215,
|
| 55 |
+
"eval_wer": 0.9294207172072672,
|
| 56 |
+
"step": 800
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.36,
|
| 60 |
+
"eval_loss": 0.8205996751785278,
|
| 61 |
+
"eval_runtime": 124.5979,
|
| 62 |
+
"eval_samples_per_second": 17.673,
|
| 63 |
+
"eval_steps_per_second": 2.215,
|
| 64 |
+
"eval_wer": 0.9016455816608009,
|
| 65 |
+
"step": 1000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 4.03,
|
| 69 |
+
"learning_rate": 0.0008718749999999999,
|
| 70 |
+
"loss": 0.617,
|
| 71 |
+
"step": 1200
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 4.03,
|
| 75 |
+
"eval_loss": 0.7664089798927307,
|
| 76 |
+
"eval_runtime": 124.9893,
|
| 77 |
+
"eval_samples_per_second": 17.618,
|
| 78 |
+
"eval_steps_per_second": 2.208,
|
| 79 |
+
"eval_wer": 0.9076381622752783,
|
| 80 |
+
"step": 1200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 4.71,
|
| 84 |
+
"eval_loss": 0.8046385049819946,
|
| 85 |
+
"eval_runtime": 124.9226,
|
| 86 |
+
"eval_samples_per_second": 17.627,
|
| 87 |
+
"eval_steps_per_second": 2.209,
|
| 88 |
+
"eval_wer": 0.902787025587368,
|
| 89 |
+
"step": 1400
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.38,
|
| 93 |
+
"learning_rate": 0.0007983455882352941,
|
| 94 |
+
"loss": 0.5312,
|
| 95 |
+
"step": 1600
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 5.38,
|
| 99 |
+
"eval_loss": 0.7806461453437805,
|
| 100 |
+
"eval_runtime": 125.1179,
|
| 101 |
+
"eval_samples_per_second": 17.599,
|
| 102 |
+
"eval_steps_per_second": 2.206,
|
| 103 |
+
"eval_wer": 0.9512983924664701,
|
| 104 |
+
"step": 1600
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.05,
|
| 108 |
+
"eval_loss": 0.7088819146156311,
|
| 109 |
+
"eval_runtime": 127.0024,
|
| 110 |
+
"eval_samples_per_second": 17.338,
|
| 111 |
+
"eval_steps_per_second": 2.173,
|
| 112 |
+
"eval_wer": 0.8616950442309521,
|
| 113 |
+
"step": 1800
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 6.72,
|
| 117 |
+
"learning_rate": 0.0007248161764705882,
|
| 118 |
+
"loss": 0.4404,
|
| 119 |
+
"step": 2000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 6.72,
|
| 123 |
+
"eval_loss": 0.7011399269104004,
|
| 124 |
+
"eval_runtime": 125.0855,
|
| 125 |
+
"eval_samples_per_second": 17.604,
|
| 126 |
+
"eval_steps_per_second": 2.206,
|
| 127 |
+
"eval_wer": 0.8952725197374679,
|
| 128 |
+
"step": 2000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 7.39,
|
| 132 |
+
"eval_loss": 0.6890342235565186,
|
| 133 |
+
"eval_runtime": 125.964,
|
| 134 |
+
"eval_samples_per_second": 17.481,
|
| 135 |
+
"eval_steps_per_second": 2.191,
|
| 136 |
+
"eval_wer": 0.8790069437838867,
|
| 137 |
+
"step": 2200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 8.07,
|
| 141 |
+
"learning_rate": 0.0006512867647058823,
|
| 142 |
+
"loss": 0.3961,
|
| 143 |
+
"step": 2400
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 8.07,
|
| 147 |
+
"eval_loss": 0.6665045619010925,
|
| 148 |
+
"eval_runtime": 125.5126,
|
| 149 |
+
"eval_samples_per_second": 17.544,
|
| 150 |
+
"eval_steps_per_second": 2.199,
|
| 151 |
+
"eval_wer": 0.8834775991629411,
|
| 152 |
+
"step": 2400
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 8.74,
|
| 156 |
+
"eval_loss": 0.6596990823745728,
|
| 157 |
+
"eval_runtime": 125.1836,
|
| 158 |
+
"eval_samples_per_second": 17.59,
|
| 159 |
+
"eval_steps_per_second": 2.205,
|
| 160 |
+
"eval_wer": 0.8537049367449824,
|
| 161 |
+
"step": 2600
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 9.41,
|
| 165 |
+
"learning_rate": 0.0005777573529411765,
|
| 166 |
+
"loss": 0.3402,
|
| 167 |
+
"step": 2800
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 9.41,
|
| 171 |
+
"eval_loss": 0.6772456765174866,
|
| 172 |
+
"eval_runtime": 125.8045,
|
| 173 |
+
"eval_samples_per_second": 17.503,
|
| 174 |
+
"eval_steps_per_second": 2.194,
|
| 175 |
+
"eval_wer": 0.8308760582136403,
|
| 176 |
+
"step": 2800
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 10.08,
|
| 180 |
+
"eval_loss": 0.6295859813690186,
|
| 181 |
+
"eval_runtime": 125.3009,
|
| 182 |
+
"eval_samples_per_second": 17.574,
|
| 183 |
+
"eval_steps_per_second": 2.203,
|
| 184 |
+
"eval_wer": 0.8315419005041378,
|
| 185 |
+
"step": 3000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 10.76,
|
| 189 |
+
"learning_rate": 0.0005042279411764706,
|
| 190 |
+
"loss": 0.2939,
|
| 191 |
+
"step": 3200
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 10.76,
|
| 195 |
+
"eval_loss": 0.6442817449569702,
|
| 196 |
+
"eval_runtime": 125.5719,
|
| 197 |
+
"eval_samples_per_second": 17.536,
|
| 198 |
+
"eval_steps_per_second": 2.198,
|
| 199 |
+
"eval_wer": 0.8326833444307048,
|
| 200 |
+
"step": 3200
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 11.43,
|
| 204 |
+
"eval_loss": 0.5965331196784973,
|
| 205 |
+
"eval_runtime": 126.3146,
|
| 206 |
+
"eval_samples_per_second": 17.433,
|
| 207 |
+
"eval_steps_per_second": 2.185,
|
| 208 |
+
"eval_wer": 0.8219347474555313,
|
| 209 |
+
"step": 3400
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 12.1,
|
| 213 |
+
"learning_rate": 0.00043069852941176473,
|
| 214 |
+
"loss": 0.2325,
|
| 215 |
+
"step": 3600
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 12.1,
|
| 219 |
+
"eval_loss": 0.613932728767395,
|
| 220 |
+
"eval_runtime": 125.4233,
|
| 221 |
+
"eval_samples_per_second": 17.557,
|
| 222 |
+
"eval_steps_per_second": 2.201,
|
| 223 |
+
"eval_wer": 0.8033862836488157,
|
| 224 |
+
"step": 3600
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 12.77,
|
| 228 |
+
"eval_loss": 0.5964781641960144,
|
| 229 |
+
"eval_runtime": 125.9783,
|
| 230 |
+
"eval_samples_per_second": 17.479,
|
| 231 |
+
"eval_steps_per_second": 2.191,
|
| 232 |
+
"eval_wer": 0.8020545990678208,
|
| 233 |
+
"step": 3800
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 13.45,
|
| 237 |
+
"learning_rate": 0.0003571691176470588,
|
| 238 |
+
"loss": 0.1823,
|
| 239 |
+
"step": 4000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 13.45,
|
| 243 |
+
"eval_loss": 0.640591561794281,
|
| 244 |
+
"eval_runtime": 125.8961,
|
| 245 |
+
"eval_samples_per_second": 17.491,
|
| 246 |
+
"eval_steps_per_second": 2.192,
|
| 247 |
+
"eval_wer": 0.8089032626272235,
|
| 248 |
+
"step": 4000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 14.12,
|
| 252 |
+
"eval_loss": 0.6114814877510071,
|
| 253 |
+
"eval_runtime": 126.0685,
|
| 254 |
+
"eval_samples_per_second": 17.467,
|
| 255 |
+
"eval_steps_per_second": 2.189,
|
| 256 |
+
"eval_wer": 0.797964424997622,
|
| 257 |
+
"step": 4200
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 14.79,
|
| 261 |
+
"learning_rate": 0.0002836397058823529,
|
| 262 |
+
"loss": 0.138,
|
| 263 |
+
"step": 4400
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 14.79,
|
| 267 |
+
"eval_loss": 0.6256727576255798,
|
| 268 |
+
"eval_runtime": 126.3311,
|
| 269 |
+
"eval_samples_per_second": 17.43,
|
| 270 |
+
"eval_steps_per_second": 2.185,
|
| 271 |
+
"eval_wer": 0.7777989156282697,
|
| 272 |
+
"step": 4400
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 15.46,
|
| 276 |
+
"eval_loss": 0.6141476035118103,
|
| 277 |
+
"eval_runtime": 126.0957,
|
| 278 |
+
"eval_samples_per_second": 17.463,
|
| 279 |
+
"eval_steps_per_second": 2.189,
|
| 280 |
+
"eval_wer": 0.7941596119090649,
|
| 281 |
+
"step": 4600
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 16.13,
|
| 285 |
+
"learning_rate": 0.00021011029411764707,
|
| 286 |
+
"loss": 0.0784,
|
| 287 |
+
"step": 4800
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 16.13,
|
| 291 |
+
"eval_loss": 0.6295885443687439,
|
| 292 |
+
"eval_runtime": 126.3665,
|
| 293 |
+
"eval_samples_per_second": 17.425,
|
| 294 |
+
"eval_steps_per_second": 2.184,
|
| 295 |
+
"eval_wer": 0.7922572053647865,
|
| 296 |
+
"step": 4800
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 16.81,
|
| 300 |
+
"eval_loss": 0.5918190479278564,
|
| 301 |
+
"eval_runtime": 126.3879,
|
| 302 |
+
"eval_samples_per_second": 17.423,
|
| 303 |
+
"eval_steps_per_second": 2.184,
|
| 304 |
+
"eval_wer": 0.7728526586131457,
|
| 305 |
+
"step": 5000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 17.48,
|
| 309 |
+
"learning_rate": 0.00013658088235294117,
|
| 310 |
+
"loss": 0.0344,
|
| 311 |
+
"step": 5200
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 17.48,
|
| 315 |
+
"eval_loss": 0.5919037461280823,
|
| 316 |
+
"eval_runtime": 126.2976,
|
| 317 |
+
"eval_samples_per_second": 17.435,
|
| 318 |
+
"eval_steps_per_second": 2.185,
|
| 319 |
+
"eval_wer": 0.7636259868733949,
|
| 320 |
+
"step": 5200
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 18.15,
|
| 324 |
+
"eval_loss": 0.576080858707428,
|
| 325 |
+
"eval_runtime": 126.7739,
|
| 326 |
+
"eval_samples_per_second": 17.37,
|
| 327 |
+
"eval_steps_per_second": 2.177,
|
| 328 |
+
"eval_wer": 0.7495481784457338,
|
| 329 |
+
"step": 5400
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 18.82,
|
| 333 |
+
"learning_rate": 6.30514705882353e-05,
|
| 334 |
+
"loss": -0.0038,
|
| 335 |
+
"step": 5600
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 18.82,
|
| 339 |
+
"eval_loss": 0.5868940949440002,
|
| 340 |
+
"eval_runtime": 126.4596,
|
| 341 |
+
"eval_samples_per_second": 17.413,
|
| 342 |
+
"eval_steps_per_second": 2.183,
|
| 343 |
+
"eval_wer": 0.7588699705126986,
|
| 344 |
+
"step": 5600
|
| 345 |
+
}
|
| 346 |
+
],
|
| 347 |
+
"max_steps": 5940,
|
| 348 |
+
"num_train_epochs": 20,
|
| 349 |
+
"total_flos": 4.6199251281753915e+19,
|
| 350 |
+
"trial_name": null,
|
| 351 |
+
"trial_params": null
|
| 352 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6b3590f03cebef8397182f292f98fc4ffd570bebea790c690e924362c819924
|
| 3 |
+
size 3899
|