add checkpoint
Browse files- checkpoint-23200/config.json +108 -0
- checkpoint-23200/optimizer.pt +3 -0
- checkpoint-23200/preprocessor_config.json +10 -0
- checkpoint-23200/pytorch_model.bin +3 -0
- checkpoint-23200/rng_state.pth +3 -0
- checkpoint-23200/scaler.pt +3 -0
- checkpoint-23200/scheduler.pt +3 -0
- checkpoint-23200/trainer_state.json +451 -0
- checkpoint-23200/training_args.bin +3 -0
checkpoint-23200/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": 0.1,
|
| 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": 0.1,
|
| 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_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": 0.075,
|
| 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": 0,
|
| 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": "4.23.1",
|
| 105 |
+
"use_weighted_layer_sum": false,
|
| 106 |
+
"vocab_size": 81,
|
| 107 |
+
"xvector_output_dim": 512
|
| 108 |
+
}
|
checkpoint-23200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83cd9fd4be36da2f4c10f34e2c00fa18aaefb83dca3e77ddd171d4f4346cf8cb
|
| 3 |
+
size 2490723217
|
checkpoint-23200/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 |
+
}
|
checkpoint-23200/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28ccb44b9b0050b3deab7672c6be94f1142f29e8a7cfd2e9a44ad1cf2260c550
|
| 3 |
+
size 1262230833
|
checkpoint-23200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b601e6f0ec4a06a754dd5aada1ad5760e3ebec6b9b8cc91e8a77189c66c590cd
|
| 3 |
+
size 14567
|
checkpoint-23200/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd84938a8dc533894c5f1831169f63a1f9719685e173c2d85b1665cab3962253
|
| 3 |
+
size 559
|
checkpoint-23200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4554d1c0ddf5d6d62163125051f91c4bc7962d82290df988bd0f7ef5890dd5b
|
| 3 |
+
size 623
|
checkpoint-23200/trainer_state.json
ADDED
|
@@ -0,0 +1,451 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.21271623770731232,
|
| 3 |
+
"best_model_checkpoint": "wav2vec2-large-xls-r-300m-nepali-openslr/checkpoint-23200",
|
| 4 |
+
"epoch": 6.066936854490783,
|
| 5 |
+
"global_step": 23200,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.21,
|
| 12 |
+
"learning_rate": 0.0002976391096979332,
|
| 13 |
+
"loss": 6.4525,
|
| 14 |
+
"step": 800
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.21,
|
| 18 |
+
"eval_loss": 1.4264159202575684,
|
| 19 |
+
"eval_runtime": 579.6055,
|
| 20 |
+
"eval_samples_per_second": 37.262,
|
| 21 |
+
"eval_steps_per_second": 4.658,
|
| 22 |
+
"eval_wer": 0.9522086267891338,
|
| 23 |
+
"step": 800
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.42,
|
| 27 |
+
"learning_rate": 0.00029127980922098566,
|
| 28 |
+
"loss": 1.105,
|
| 29 |
+
"step": 1600
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.42,
|
| 33 |
+
"eval_loss": 0.5966897010803223,
|
| 34 |
+
"eval_runtime": 638.739,
|
| 35 |
+
"eval_samples_per_second": 33.812,
|
| 36 |
+
"eval_steps_per_second": 4.227,
|
| 37 |
+
"eval_wer": 0.6514394209860115,
|
| 38 |
+
"step": 1600
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.63,
|
| 42 |
+
"learning_rate": 0.00028492050874403814,
|
| 43 |
+
"loss": 0.7933,
|
| 44 |
+
"step": 2400
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.63,
|
| 48 |
+
"eval_loss": 0.44666677713394165,
|
| 49 |
+
"eval_runtime": 578.27,
|
| 50 |
+
"eval_samples_per_second": 37.348,
|
| 51 |
+
"eval_steps_per_second": 4.669,
|
| 52 |
+
"eval_wer": 0.5045276037778715,
|
| 53 |
+
"step": 2400
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.84,
|
| 57 |
+
"learning_rate": 0.00027856120826709056,
|
| 58 |
+
"loss": 0.6926,
|
| 59 |
+
"step": 3200
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.84,
|
| 63 |
+
"eval_loss": 0.3889370858669281,
|
| 64 |
+
"eval_runtime": 574.1787,
|
| 65 |
+
"eval_samples_per_second": 37.614,
|
| 66 |
+
"eval_steps_per_second": 4.702,
|
| 67 |
+
"eval_wer": 0.4508941611762033,
|
| 68 |
+
"step": 3200
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.05,
|
| 72 |
+
"learning_rate": 0.0002722019077901431,
|
| 73 |
+
"loss": 0.6258,
|
| 74 |
+
"step": 4000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.05,
|
| 78 |
+
"eval_loss": 0.33456486463546753,
|
| 79 |
+
"eval_runtime": 575.0581,
|
| 80 |
+
"eval_samples_per_second": 37.556,
|
| 81 |
+
"eval_steps_per_second": 4.695,
|
| 82 |
+
"eval_wer": 0.39778001363149523,
|
| 83 |
+
"step": 4000
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.26,
|
| 87 |
+
"learning_rate": 0.0002658426073131955,
|
| 88 |
+
"loss": 0.5666,
|
| 89 |
+
"step": 4800
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.26,
|
| 93 |
+
"eval_loss": 0.31256240606307983,
|
| 94 |
+
"eval_runtime": 592.8115,
|
| 95 |
+
"eval_samples_per_second": 36.431,
|
| 96 |
+
"eval_steps_per_second": 4.555,
|
| 97 |
+
"eval_wer": 0.3761481289149979,
|
| 98 |
+
"step": 4800
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.46,
|
| 102 |
+
"learning_rate": 0.000259483306836248,
|
| 103 |
+
"loss": 0.5501,
|
| 104 |
+
"step": 5600
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.46,
|
| 108 |
+
"eval_loss": 0.2980588376522064,
|
| 109 |
+
"eval_runtime": 662.1285,
|
| 110 |
+
"eval_samples_per_second": 32.618,
|
| 111 |
+
"eval_steps_per_second": 4.078,
|
| 112 |
+
"eval_wer": 0.3593684073869722,
|
| 113 |
+
"step": 5600
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.67,
|
| 117 |
+
"learning_rate": 0.00025313195548489663,
|
| 118 |
+
"loss": 0.5275,
|
| 119 |
+
"step": 6400
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.67,
|
| 123 |
+
"eval_loss": 0.28137603402137756,
|
| 124 |
+
"eval_runtime": 588.9138,
|
| 125 |
+
"eval_samples_per_second": 36.673,
|
| 126 |
+
"eval_steps_per_second": 4.585,
|
| 127 |
+
"eval_wer": 0.3457206841712375,
|
| 128 |
+
"step": 6400
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.88,
|
| 132 |
+
"learning_rate": 0.0002467726550079491,
|
| 133 |
+
"loss": 0.5203,
|
| 134 |
+
"step": 7200
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.88,
|
| 138 |
+
"eval_loss": 0.2654956877231598,
|
| 139 |
+
"eval_runtime": 586.4688,
|
| 140 |
+
"eval_samples_per_second": 36.825,
|
| 141 |
+
"eval_steps_per_second": 4.604,
|
| 142 |
+
"eval_wer": 0.3303041121677323,
|
| 143 |
+
"step": 7200
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 2.09,
|
| 147 |
+
"learning_rate": 0.00024041335453100157,
|
| 148 |
+
"loss": 0.4842,
|
| 149 |
+
"step": 8000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 2.09,
|
| 153 |
+
"eval_loss": 0.2574324607849121,
|
| 154 |
+
"eval_runtime": 641.5915,
|
| 155 |
+
"eval_samples_per_second": 33.662,
|
| 156 |
+
"eval_steps_per_second": 4.208,
|
| 157 |
+
"eval_wer": 0.31566648274966735,
|
| 158 |
+
"step": 8000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.3,
|
| 162 |
+
"learning_rate": 0.00023405405405405404,
|
| 163 |
+
"loss": 0.4542,
|
| 164 |
+
"step": 8800
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.3,
|
| 168 |
+
"eval_loss": 0.2577317953109741,
|
| 169 |
+
"eval_runtime": 583.455,
|
| 170 |
+
"eval_samples_per_second": 37.016,
|
| 171 |
+
"eval_steps_per_second": 4.628,
|
| 172 |
+
"eval_wer": 0.31417350946090683,
|
| 173 |
+
"step": 8800
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 2.51,
|
| 177 |
+
"learning_rate": 0.0002276947535771065,
|
| 178 |
+
"loss": 0.4431,
|
| 179 |
+
"step": 9600
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.51,
|
| 183 |
+
"eval_loss": 0.23904646933078766,
|
| 184 |
+
"eval_runtime": 581.9022,
|
| 185 |
+
"eval_samples_per_second": 37.114,
|
| 186 |
+
"eval_steps_per_second": 4.64,
|
| 187 |
+
"eval_wer": 0.2938236344162799,
|
| 188 |
+
"step": 9600
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.72,
|
| 192 |
+
"learning_rate": 0.00022133545310015898,
|
| 193 |
+
"loss": 0.4235,
|
| 194 |
+
"step": 10400
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.72,
|
| 198 |
+
"eval_loss": 0.24016053974628448,
|
| 199 |
+
"eval_runtime": 582.7306,
|
| 200 |
+
"eval_samples_per_second": 37.062,
|
| 201 |
+
"eval_steps_per_second": 4.633,
|
| 202 |
+
"eval_wer": 0.2884684041413781,
|
| 203 |
+
"step": 10400
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.93,
|
| 207 |
+
"learning_rate": 0.0002149920508744038,
|
| 208 |
+
"loss": 0.4202,
|
| 209 |
+
"step": 11200
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.93,
|
| 213 |
+
"eval_loss": 0.22816315293312073,
|
| 214 |
+
"eval_runtime": 643.2534,
|
| 215 |
+
"eval_samples_per_second": 33.575,
|
| 216 |
+
"eval_steps_per_second": 4.197,
|
| 217 |
+
"eval_wer": 0.2846710590373568,
|
| 218 |
+
"step": 11200
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.14,
|
| 222 |
+
"learning_rate": 0.00020863275039745627,
|
| 223 |
+
"loss": 0.4018,
|
| 224 |
+
"step": 12000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.14,
|
| 228 |
+
"eval_loss": 0.22759725153446198,
|
| 229 |
+
"eval_runtime": 584.1242,
|
| 230 |
+
"eval_samples_per_second": 36.973,
|
| 231 |
+
"eval_steps_per_second": 4.622,
|
| 232 |
+
"eval_wer": 0.27702768491772417,
|
| 233 |
+
"step": 12000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 3.35,
|
| 237 |
+
"learning_rate": 0.00020227344992050872,
|
| 238 |
+
"loss": 0.3986,
|
| 239 |
+
"step": 12800
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 3.35,
|
| 243 |
+
"eval_loss": 0.224422425031662,
|
| 244 |
+
"eval_runtime": 582.249,
|
| 245 |
+
"eval_samples_per_second": 37.092,
|
| 246 |
+
"eval_steps_per_second": 4.637,
|
| 247 |
+
"eval_wer": 0.27022816526565185,
|
| 248 |
+
"step": 12800
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.56,
|
| 252 |
+
"learning_rate": 0.00019591414944356117,
|
| 253 |
+
"loss": 0.3792,
|
| 254 |
+
"step": 13600
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.56,
|
| 258 |
+
"eval_loss": 0.21611596643924713,
|
| 259 |
+
"eval_runtime": 589.0669,
|
| 260 |
+
"eval_samples_per_second": 36.663,
|
| 261 |
+
"eval_steps_per_second": 4.584,
|
| 262 |
+
"eval_wer": 0.2742527019570932,
|
| 263 |
+
"step": 13600
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.77,
|
| 267 |
+
"learning_rate": 0.00018955484896661365,
|
| 268 |
+
"loss": 0.3736,
|
| 269 |
+
"step": 14400
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 3.77,
|
| 273 |
+
"eval_loss": 0.20533400774002075,
|
| 274 |
+
"eval_runtime": 644.3789,
|
| 275 |
+
"eval_samples_per_second": 33.516,
|
| 276 |
+
"eval_steps_per_second": 4.19,
|
| 277 |
+
"eval_wer": 0.2546979974684366,
|
| 278 |
+
"step": 14400
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.97,
|
| 282 |
+
"learning_rate": 0.0001831955484896661,
|
| 283 |
+
"loss": 0.37,
|
| 284 |
+
"step": 15200
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.97,
|
| 288 |
+
"eval_loss": 0.19958257675170898,
|
| 289 |
+
"eval_runtime": 585.9573,
|
| 290 |
+
"eval_samples_per_second": 36.858,
|
| 291 |
+
"eval_steps_per_second": 4.608,
|
| 292 |
+
"eval_wer": 0.25521729252539677,
|
| 293 |
+
"step": 15200
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 4.18,
|
| 297 |
+
"learning_rate": 0.00017683624801271858,
|
| 298 |
+
"loss": 0.3499,
|
| 299 |
+
"step": 16000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 4.18,
|
| 303 |
+
"eval_loss": 0.19865886867046356,
|
| 304 |
+
"eval_runtime": 587.8211,
|
| 305 |
+
"eval_samples_per_second": 36.741,
|
| 306 |
+
"eval_steps_per_second": 4.593,
|
| 307 |
+
"eval_wer": 0.24392262503651294,
|
| 308 |
+
"step": 16000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 4.39,
|
| 312 |
+
"learning_rate": 0.00017048489666136724,
|
| 313 |
+
"loss": 0.3416,
|
| 314 |
+
"step": 16800
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 4.39,
|
| 318 |
+
"eval_loss": 0.1961081475019455,
|
| 319 |
+
"eval_runtime": 586.8214,
|
| 320 |
+
"eval_samples_per_second": 36.803,
|
| 321 |
+
"eval_steps_per_second": 4.601,
|
| 322 |
+
"eval_wer": 0.24739541072993412,
|
| 323 |
+
"step": 16800
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 4.6,
|
| 327 |
+
"learning_rate": 0.0001641255961844197,
|
| 328 |
+
"loss": 0.3329,
|
| 329 |
+
"step": 17600
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 4.6,
|
| 333 |
+
"eval_loss": 0.19132652878761292,
|
| 334 |
+
"eval_runtime": 586.4075,
|
| 335 |
+
"eval_samples_per_second": 36.829,
|
| 336 |
+
"eval_steps_per_second": 4.604,
|
| 337 |
+
"eval_wer": 0.2405309791957418,
|
| 338 |
+
"step": 17600
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.81,
|
| 342 |
+
"learning_rate": 0.00015776629570747217,
|
| 343 |
+
"loss": 0.3204,
|
| 344 |
+
"step": 18400
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 4.81,
|
| 348 |
+
"eval_loss": 0.18798914551734924,
|
| 349 |
+
"eval_runtime": 588.6226,
|
| 350 |
+
"eval_samples_per_second": 36.691,
|
| 351 |
+
"eval_steps_per_second": 4.587,
|
| 352 |
+
"eval_wer": 0.23799941579306091,
|
| 353 |
+
"step": 18400
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 5.02,
|
| 357 |
+
"learning_rate": 0.00015141494435612083,
|
| 358 |
+
"loss": 0.3117,
|
| 359 |
+
"step": 19200
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 5.02,
|
| 363 |
+
"eval_loss": 0.18481141328811646,
|
| 364 |
+
"eval_runtime": 585.979,
|
| 365 |
+
"eval_samples_per_second": 36.856,
|
| 366 |
+
"eval_steps_per_second": 4.608,
|
| 367 |
+
"eval_wer": 0.23517574892083995,
|
| 368 |
+
"step": 19200
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 5.23,
|
| 372 |
+
"learning_rate": 0.00014505564387917329,
|
| 373 |
+
"loss": 0.3047,
|
| 374 |
+
"step": 20000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 5.23,
|
| 378 |
+
"eval_loss": 0.18402975797653198,
|
| 379 |
+
"eval_runtime": 599.835,
|
| 380 |
+
"eval_samples_per_second": 36.005,
|
| 381 |
+
"eval_steps_per_second": 4.501,
|
| 382 |
+
"eval_wer": 0.23626302294635032,
|
| 383 |
+
"step": 20000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 5.44,
|
| 387 |
+
"learning_rate": 0.00013869634340222574,
|
| 388 |
+
"loss": 0.3024,
|
| 389 |
+
"step": 20800
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 5.44,
|
| 393 |
+
"eval_loss": 0.18139642477035522,
|
| 394 |
+
"eval_runtime": 677.1234,
|
| 395 |
+
"eval_samples_per_second": 31.895,
|
| 396 |
+
"eval_steps_per_second": 3.987,
|
| 397 |
+
"eval_wer": 0.22464379604686638,
|
| 398 |
+
"step": 20800
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 5.65,
|
| 402 |
+
"learning_rate": 0.00013233704292527822,
|
| 403 |
+
"loss": 0.298,
|
| 404 |
+
"step": 21600
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 5.65,
|
| 408 |
+
"eval_loss": 0.17222227156162262,
|
| 409 |
+
"eval_runtime": 599.2372,
|
| 410 |
+
"eval_samples_per_second": 36.041,
|
| 411 |
+
"eval_steps_per_second": 4.506,
|
| 412 |
+
"eval_wer": 0.21863944695076434,
|
| 413 |
+
"step": 21600
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 5.86,
|
| 417 |
+
"learning_rate": 0.00012598569157392685,
|
| 418 |
+
"loss": 0.293,
|
| 419 |
+
"step": 22400
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 5.86,
|
| 423 |
+
"eval_loss": 0.16723385453224182,
|
| 424 |
+
"eval_runtime": 593.0988,
|
| 425 |
+
"eval_samples_per_second": 36.414,
|
| 426 |
+
"eval_steps_per_second": 4.552,
|
| 427 |
+
"eval_wer": 0.21511797734575314,
|
| 428 |
+
"step": 22400
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 6.07,
|
| 432 |
+
"learning_rate": 0.00011962639109697933,
|
| 433 |
+
"loss": 0.2819,
|
| 434 |
+
"step": 23200
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 6.07,
|
| 438 |
+
"eval_loss": 0.17666752636432648,
|
| 439 |
+
"eval_runtime": 595.3962,
|
| 440 |
+
"eval_samples_per_second": 36.273,
|
| 441 |
+
"eval_steps_per_second": 4.535,
|
| 442 |
+
"eval_wer": 0.21271623770731232,
|
| 443 |
+
"step": 23200
|
| 444 |
+
}
|
| 445 |
+
],
|
| 446 |
+
"max_steps": 38240,
|
| 447 |
+
"num_train_epochs": 10,
|
| 448 |
+
"total_flos": 7.369934202144359e+19,
|
| 449 |
+
"trial_name": null,
|
| 450 |
+
"trial_params": null
|
| 451 |
+
}
|
checkpoint-23200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:037dd272920861623d6bc3135be9cc30f9bde00519d31349fd89a53eb0dda9a2
|
| 3 |
+
size 3439
|