marinone94
commited on
Commit
•
695f499
1
Parent(s):
6103913
End of training
Browse files- all_results.json +14 -0
- checkpoint-5/config.json +0 -96
- checkpoint-5/optimizer.pt +0 -3
- checkpoint-5/preprocessor_config.json +0 -9
- checkpoint-5/pytorch_model.bin +0 -3
- checkpoint-5/rng_state.pth +0 -3
- checkpoint-5/scheduler.pt +0 -3
- checkpoint-5/training_args.bin +0 -3
- eval_results.json +9 -0
- train_results.json +8 -0
- checkpoint-5/trainer_state.json → trainer_state.json +14 -4
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.03,
|
3 |
+
"eval_loss": 155.7938690185547,
|
4 |
+
"eval_runtime": 55.6971,
|
5 |
+
"eval_samples": 301,
|
6 |
+
"eval_samples_per_second": 5.404,
|
7 |
+
"eval_steps_per_second": 0.682,
|
8 |
+
"eval_wer": 1.084206116464181,
|
9 |
+
"train_loss": 93.28157958984374,
|
10 |
+
"train_runtime": 23.9574,
|
11 |
+
"train_samples": 704,
|
12 |
+
"train_samples_per_second": 0.835,
|
13 |
+
"train_steps_per_second": 0.417
|
14 |
+
}
|
checkpoint-5/config.json
DELETED
@@ -1,96 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "hf-test/xls-r-dummy",
|
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": 256,
|
15 |
-
"contrastive_logits_temperature": 0.1,
|
16 |
-
"conv_bias": false,
|
17 |
-
"conv_dim": [
|
18 |
-
32,
|
19 |
-
32,
|
20 |
-
32
|
21 |
-
],
|
22 |
-
"conv_kernel": [
|
23 |
-
8,
|
24 |
-
8,
|
25 |
-
8
|
26 |
-
],
|
27 |
-
"conv_stride": [
|
28 |
-
4,
|
29 |
-
4,
|
30 |
-
4
|
31 |
-
],
|
32 |
-
"ctc_loss_reduction": "mean",
|
33 |
-
"ctc_zero_infinity": false,
|
34 |
-
"diversity_loss_weight": 0.1,
|
35 |
-
"do_stable_layer_norm": true,
|
36 |
-
"eos_token_id": 2,
|
37 |
-
"feat_extract_activation": "gelu",
|
38 |
-
"feat_extract_dropout": 0.0,
|
39 |
-
"feat_extract_norm": "layer",
|
40 |
-
"feat_proj_dropout": 0.0,
|
41 |
-
"feat_quantizer_dropout": 0.0,
|
42 |
-
"final_dropout": 0.0,
|
43 |
-
"hidden_act": "gelu",
|
44 |
-
"hidden_dropout": 0.0,
|
45 |
-
"hidden_dropout_prob": 0.1,
|
46 |
-
"hidden_size": 16,
|
47 |
-
"initializer_range": 0.02,
|
48 |
-
"intermediate_size": 20,
|
49 |
-
"layer_norm_eps": 1e-05,
|
50 |
-
"layerdrop": 0.0,
|
51 |
-
"mask_feature_length": 10,
|
52 |
-
"mask_feature_min_masks": 0,
|
53 |
-
"mask_feature_prob": 0.0,
|
54 |
-
"mask_time_length": 10,
|
55 |
-
"mask_time_min_masks": 2,
|
56 |
-
"mask_time_prob": 0.05,
|
57 |
-
"model_type": "wav2vec2",
|
58 |
-
"num_adapter_layers": 3,
|
59 |
-
"num_attention_heads": 2,
|
60 |
-
"num_codevector_groups": 2,
|
61 |
-
"num_codevectors_per_group": 320,
|
62 |
-
"num_conv_pos_embedding_groups": 2,
|
63 |
-
"num_conv_pos_embeddings": 16,
|
64 |
-
"num_feat_extract_layers": 3,
|
65 |
-
"num_hidden_layers": 4,
|
66 |
-
"num_negatives": 10,
|
67 |
-
"output_hidden_size": 16,
|
68 |
-
"pad_token_id": 50,
|
69 |
-
"proj_codevector_dim": 256,
|
70 |
-
"tdnn_dilation": [
|
71 |
-
1,
|
72 |
-
2,
|
73 |
-
3,
|
74 |
-
1,
|
75 |
-
1
|
76 |
-
],
|
77 |
-
"tdnn_dim": [
|
78 |
-
512,
|
79 |
-
512,
|
80 |
-
512,
|
81 |
-
512,
|
82 |
-
1500
|
83 |
-
],
|
84 |
-
"tdnn_kernel": [
|
85 |
-
5,
|
86 |
-
3,
|
87 |
-
3,
|
88 |
-
1,
|
89 |
-
1
|
90 |
-
],
|
91 |
-
"torch_dtype": "float32",
|
92 |
-
"transformers_version": "4.16.0.dev0",
|
93 |
-
"use_weighted_layer_sum": false,
|
94 |
-
"vocab_size": 53,
|
95 |
-
"xvector_output_dim": 512
|
96 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-5/optimizer.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:8e671769d8e7c6e50fda9751a0d3f50d1ad0a5867a3186328dbbea2c27bb8aaf
|
3 |
-
size 128273
|
|
|
|
|
|
|
|
checkpoint-5/preprocessor_config.json
DELETED
@@ -1,9 +0,0 @@
|
|
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": false,
|
8 |
-
"sampling_rate": 16000
|
9 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-5/pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:fd01668f7ea1961fb498356d85e789d5b8ebe359ff437cea5845060c64f8eaa3
|
3 |
-
size 142694
|
|
|
|
|
|
|
|
checkpoint-5/rng_state.pth
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:95b51a631a60af2739cb31adbae099700ec09270ddb7a7e50d2fca34dafca4ce
|
3 |
-
size 13611
|
|
|
|
|
|
|
|
checkpoint-5/scheduler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:59216c25b5b10e66c1be135b3804bb7b79f89ad700aea4e78300a0b0e97a9507
|
3 |
-
size 623
|
|
|
|
|
|
|
|
checkpoint-5/training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:0d984518be407c10d2f161021e8f4824522fcbc805d42098d3c9a603e88255e3
|
3 |
-
size 2991
|
|
|
|
|
|
|
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.03,
|
3 |
+
"eval_loss": 155.7938690185547,
|
4 |
+
"eval_runtime": 55.6971,
|
5 |
+
"eval_samples": 301,
|
6 |
+
"eval_samples_per_second": 5.404,
|
7 |
+
"eval_steps_per_second": 0.682,
|
8 |
+
"eval_wer": 1.084206116464181
|
9 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.03,
|
3 |
+
"train_loss": 93.28157958984374,
|
4 |
+
"train_runtime": 23.9574,
|
5 |
+
"train_samples": 704,
|
6 |
+
"train_samples_per_second": 0.835,
|
7 |
+
"train_steps_per_second": 0.417
|
8 |
+
}
|
checkpoint-5/trainer_state.json → trainer_state.json
RENAMED
@@ -1,15 +1,25 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
-
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
"max_steps": 10,
|
11 |
"num_train_epochs": 1,
|
12 |
-
"total_flos":
|
13 |
"trial_name": null,
|
14 |
"trial_params": null
|
15 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.028409090909090908,
|
5 |
+
"global_step": 10,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.03,
|
12 |
+
"step": 10,
|
13 |
+
"total_flos": 508182128640.0,
|
14 |
+
"train_loss": 93.28157958984374,
|
15 |
+
"train_runtime": 23.9574,
|
16 |
+
"train_samples_per_second": 0.835,
|
17 |
+
"train_steps_per_second": 0.417
|
18 |
+
}
|
19 |
+
],
|
20 |
"max_steps": 10,
|
21 |
"num_train_epochs": 1,
|
22 |
+
"total_flos": 508182128640.0,
|
23 |
"trial_name": null,
|
24 |
"trial_params": null
|
25 |
}
|