Hugging Face's logo

tachiwin
/
language_classification_curricular_checkpoints

Automatic Speech Recognition
Transformers
Safetensors
whisper
unsloth
Generated from Trainer
Model card Files
xet
Community
ljcamargo commited on
Commit
1da34af
·
verified ·
1 Parent(s): 59faa3e

Training in progress, step 10, checkpoint

Browse files
Files changed (10) hide show
  1. last-checkpoint/config.json +49 -0
  2. last-checkpoint/generation_config.json +151 -0
  3. last-checkpoint/model.safetensors +3 -0
  4. last-checkpoint/optimizer.pt +3 -0
  5. last-checkpoint/preprocessor_config.json +15 -0
  6. last-checkpoint/rng_state.pth +3 -0
  7. last-checkpoint/scaler.pt +3 -0
  8. last-checkpoint/scheduler.pt +3 -0
  9. last-checkpoint/trainer_state.json +63 -0
  10. last-checkpoint/training_args.bin +3 -0
last-checkpoint/config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu",
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "WhisperForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "begin_suppress_tokens": [
10
+ 220,
11
+ 50256
12
+ ],
13
+ "bos_token_id": 50257,
14
+ "classifier_proj_size": 256,
15
+ "d_model": 1280,
16
+ "decoder_attention_heads": 20,
17
+ "decoder_ffn_dim": 5120,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 4,
20
+ "decoder_start_token_id": 50258,
21
+ "dropout": 0.0,
22
+ "dtype": "float32",
23
+ "encoder_attention_heads": 20,
24
+ "encoder_ffn_dim": 5120,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 32,
27
+ "eos_token_id": 50257,
28
+ "init_std": 0.02,
29
+ "is_encoder_decoder": true,
30
+ "mask_feature_length": 10,
31
+ "mask_feature_min_masks": 0,
32
+ "mask_feature_prob": 0.0,
33
+ "mask_time_length": 10,
34
+ "mask_time_min_masks": 2,
35
+ "mask_time_prob": 0.05,
36
+ "max_source_positions": 1500,
37
+ "max_target_positions": 448,
38
+ "median_filter_width": 7,
39
+ "model_type": "whisper",
40
+ "num_hidden_layers": 32,
41
+ "num_mel_bins": 128,
42
+ "pad_token_id": 50257,
43
+ "scale_embedding": false,
44
+ "transformers_version": "4.56.2",
45
+ "unsloth_version": "2025.12.8",
46
+ "use_cache": true,
47
+ "use_weighted_layer_sum": false,
48
+ "vocab_size": 52305
49
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 2,
5
+ 4
6
+ ],
7
+ [
8
+ 2,
9
+ 11
10
+ ],
11
+ [
12
+ 3,
13
+ 3
14
+ ],
15
+ [
16
+ 3,
17
+ 6
18
+ ],
19
+ [
20
+ 3,
21
+ 11
22
+ ],
23
+ [
24
+ 3,
25
+ 14
26
+ ]
27
+ ],
28
+ "begin_suppress_tokens": [
29
+ 220,
30
+ 50257
31
+ ],
32
+ "bos_token_id": 50257,
33
+ "decoder_start_token_id": 50258,
34
+ "eos_token_id": 50257,
35
+ "forced_decoder_ids": null,
36
+ "is_multilingual": true,
37
+ "lang_to_id": {
38
+ "<|af|>": 50327,
39
+ "<|am|>": 50334,
40
+ "<|ar|>": 50272,
41
+ "<|as|>": 50350,
42
+ "<|az|>": 50304,
43
+ "<|ba|>": 50355,
44
+ "<|be|>": 50330,
45
+ "<|bg|>": 50292,
46
+ "<|bn|>": 50302,
47
+ "<|bo|>": 50347,
48
+ "<|br|>": 50309,
49
+ "<|bs|>": 50315,
50
+ "<|ca|>": 50270,
51
+ "<|cs|>": 50283,
52
+ "<|cy|>": 50297,
53
+ "<|da|>": 50285,
54
+ "<|de|>": 50261,
55
+ "<|el|>": 50281,
56
+ "<|en|>": 50259,
57
+ "<|es|>": 50262,
58
+ "<|et|>": 50307,
59
+ "<|eu|>": 50310,
60
+ "<|fa|>": 50300,
61
+ "<|fi|>": 50277,
62
+ "<|fo|>": 50338,
63
+ "<|fr|>": 50265,
64
+ "<|gl|>": 50319,
65
+ "<|gu|>": 50333,
66
+ "<|haw|>": 50352,
67
+ "<|ha|>": 50354,
68
+ "<|he|>": 50279,
69
+ "<|hi|>": 50276,
70
+ "<|hr|>": 50291,
71
+ "<|ht|>": 50339,
72
+ "<|hu|>": 50286,
73
+ "<|hy|>": 50312,
74
+ "<|id|>": 50275,
75
+ "<|is|>": 50311,
76
+ "<|it|>": 50274,
77
+ "<|ja|>": 50266,
78
+ "<|jw|>": 50356,
79
+ "<|ka|>": 50329,
80
+ "<|kk|>": 50316,
81
+ "<|km|>": 50323,
82
+ "<|kn|>": 50306,
83
+ "<|ko|>": 50264,
84
+ "<|la|>": 50294,
85
+ "<|lb|>": 50345,
86
+ "<|ln|>": 50353,
87
+ "<|lo|>": 50336,
88
+ "<|lt|>": 50293,
89
+ "<|lv|>": 50301,
90
+ "<|mg|>": 50349,
91
+ "<|mi|>": 50295,
92
+ "<|mk|>": 50308,
93
+ "<|ml|>": 50296,
94
+ "<|mn|>": 50314,
95
+ "<|mr|>": 50320,
96
+ "<|ms|>": 50282,
97
+ "<|mt|>": 50343,
98
+ "<|my|>": 50346,
99
+ "<|ne|>": 50313,
100
+ "<|nl|>": 50271,
101
+ "<|nn|>": 50342,
102
+ "<|no|>": 50288,
103
+ "<|oc|>": 50328,
104
+ "<|pa|>": 50321,
105
+ "<|pl|>": 50269,
106
+ "<|ps|>": 50340,
107
+ "<|pt|>": 50267,
108
+ "<|ro|>": 50284,
109
+ "<|ru|>": 50263,
110
+ "<|sa|>": 50344,
111
+ "<|sd|>": 50332,
112
+ "<|si|>": 50322,
113
+ "<|sk|>": 50298,
114
+ "<|sl|>": 50305,
115
+ "<|sn|>": 50324,
116
+ "<|so|>": 50326,
117
+ "<|sq|>": 50317,
118
+ "<|sr|>": 50303,
119
+ "<|su|>": 50357,
120
+ "<|sv|>": 50273,
121
+ "<|sw|>": 50318,
122
+ "<|ta|>": 50287,
123
+ "<|te|>": 50299,
124
+ "<|tg|>": 50331,
125
+ "<|th|>": 50289,
126
+ "<|tk|>": 50341,
127
+ "<|tl|>": 50348,
128
+ "<|tr|>": 50268,
129
+ "<|tt|>": 50351,
130
+ "<|uk|>": 50280,
131
+ "<|ur|>": 50290,
132
+ "<|uz|>": 50337,
133
+ "<|vi|>": 50278,
134
+ "<|yi|>": 50335,
135
+ "<|yo|>": 50325,
136
+ "<|yue|>": 50358,
137
+ "<|zh|>": 50260
138
+ },
139
+ "max_initial_timestamp_index": 50,
140
+ "max_length": 448,
141
+ "no_timestamps_token_id": 50364,
142
+ "pad_token_id": 50257,
143
+ "prev_sot_token_id": 50362,
144
+ "return_timestamps": false,
145
+ "suppress_tokens": [],
146
+ "task_to_id": {
147
+ "transcribe": 50360,
148
+ "translate": 50359
149
+ },
150
+ "transformers_version": "4.56.2"
151
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713314fbb852d3681bdd457c456fa92a5a4b8f17efc7bc30d7fc0ec6809d1ff5
3
+ size 3237829088
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbccf36e4132dbd5bfad71a220b9bc80d7b97ebac7515e599e55da6e4237b7ec
3
+ size 2061569879
last-checkpoint/preprocessor_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "dither": 0.0,
4
+ "feature_extractor_type": "WhisperFeatureExtractor",
5
+ "feature_size": 128,
6
+ "hop_length": 160,
7
+ "n_fft": 400,
8
+ "n_samples": 480000,
9
+ "nb_max_frames": 3000,
10
+ "padding_side": "right",
11
+ "padding_value": 0.0,
12
+ "processor_class": "WhisperProcessor",
13
+ "return_attention_mask": false,
14
+ "sampling_rate": 16000
15
+ }
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ddcedc173fc7bb8e4ee485559862a6e8da9544760dc1271958b7826bc1aa45c
3
+ size 14645
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dde406fb39dc0bbced01120a84cbcd1c773bea6ac49dca8cecd1a0e473d9d2af
3
+ size 1383
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dcd7c5d64c278e09f29d8b235153f3bb9756409cbc039ad08add43eb299009c
3
+ size 1465
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.003826286588865506,
6
+ "eval_steps": 10,
7
+ "global_step": 10,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.001913143294432753,
14
+ "grad_norm": 427.26959228515625,
15
+ "learning_rate": 1.9230769230769234e-06,
16
+ "loss": 13.9595,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.003826286588865506,
21
+ "grad_norm": 119.46376037597656,
22
+ "learning_rate": 1.153846153846154e-05,
23
+ "loss": 10.2278,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.003826286588865506,
28
+ "eval_avg_tokens": 300.0,
29
+ "eval_code": 0.0,
30
+ "eval_exact": 0.0,
31
+ "eval_family": 0.0,
32
+ "eval_loss": 7.974108695983887,
33
+ "eval_runtime": 177.0011,
34
+ "eval_samples": 300,
35
+ "eval_samples_per_second": 1.695,
36
+ "eval_steps_per_second": 1.695,
37
+ "eval_super": 0.0,
38
+ "eval_total_tokens": 90000,
39
+ "step": 10
40
+ }
41
+ ],
42
+ "logging_steps": 5,
43
+ "max_steps": 2614,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 1,
46
+ "save_steps": 10,
47
+ "stateful_callbacks": {
48
+ "TrainerControl": {
49
+ "args": {
50
+ "should_epoch_stop": false,
51
+ "should_evaluate": false,
52
+ "should_log": false,
53
+ "should_save": true,
54
+ "should_training_stop": false
55
+ },
56
+ "attributes": {}
57
+ }
58
+ },
59
+ "total_flos": 5.455843688448e+17,
60
+ "train_batch_size": 8,
61
+ "trial_name": null,
62
+ "trial_params": null
63
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57daf0b268e8db59107450b9b389ae9a34cdc454dce4f97c225a22e1e1824297
3
+ size 5969