SamagraDataGov commited on
Commit
33dde45
1 Parent(s): 8e8bd44

Training in progress, step 40

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44db6d4568d88eb44e51d0f265ca742133a3692240ae7207506cc0f7a0e75e81
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35d571fe5d59ea1e12e9a131ad87fc2ae0cc95f93069e66a92a882773462ccab
3
  size 151061672
runs/Jun19_22-32-24_bharatsahaiyak-test/events.out.tfevents.1718836344.bharatsahaiyak-test.422770.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc76fe49e19efc5f5fcccfee242a3e9fce8e65d7c571886d70a39454db49488d
3
+ size 6044
runs/Jun20_05-30-45_bharatsahaiyak-test/events.out.tfevents.1718861446.bharatsahaiyak-test.471347.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d442eb775d65605a5cabaa49c274315d892f3b8c368a8503a14fbadbaff5981
3
+ size 5657
runs/Jun20_05-34-22_bharatsahaiyak-test/events.out.tfevents.1718861663.bharatsahaiyak-test.474181.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37734056a8f08b5952a9925ac33ae0303b8200d60d392db8131205f96031b7c0
3
+ size 6383
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1aec3cfa20e32c0a96e76f672e29654180705b55d7cc08a87ff8f1929383e893
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:785f8e71d320f74c156379b1d499a06a784afaf0ce589664ad6e5219e0f25487
3
  size 5240
whisper-tiny-hi-checkpoint-1/trainer_state.json ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 65.3061224489796,
3
+ "best_model_checkpoint": "./whisper-tiny-hi2_test/checkpoint-200",
4
+ "epoch": 6.25,
5
+ "eval_steps": 40,
6
+ "global_step": 200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.625,
13
+ "grad_norm": 10.625165939331055,
14
+ "learning_rate": 1e-05,
15
+ "loss": 2.3669,
16
+ "step": 20
17
+ },
18
+ {
19
+ "epoch": 1.25,
20
+ "grad_norm": 7.56988525390625,
21
+ "learning_rate": 1e-05,
22
+ "loss": 1.1886,
23
+ "step": 40
24
+ },
25
+ {
26
+ "epoch": 1.25,
27
+ "eval_loss": 0.9953416585922241,
28
+ "eval_runtime": 569.1534,
29
+ "eval_samples_per_second": 1.757,
30
+ "eval_steps_per_second": 1.757,
31
+ "eval_wer": 87.39097298670505,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 1.875,
36
+ "grad_norm": 6.930533409118652,
37
+ "learning_rate": 1e-05,
38
+ "loss": 0.855,
39
+ "step": 60
40
+ },
41
+ {
42
+ "epoch": 2.5,
43
+ "grad_norm": 6.594748020172119,
44
+ "learning_rate": 1e-05,
45
+ "loss": 0.6663,
46
+ "step": 80
47
+ },
48
+ {
49
+ "epoch": 2.5,
50
+ "eval_loss": 0.6780995726585388,
51
+ "eval_runtime": 553.0571,
52
+ "eval_samples_per_second": 1.808,
53
+ "eval_steps_per_second": 1.808,
54
+ "eval_wer": 73.2153442289779,
55
+ "step": 80
56
+ },
57
+ {
58
+ "epoch": 3.125,
59
+ "grad_norm": 6.1022748947143555,
60
+ "learning_rate": 1e-05,
61
+ "loss": 0.5761,
62
+ "step": 100
63
+ },
64
+ {
65
+ "epoch": 3.75,
66
+ "grad_norm": 5.41855525970459,
67
+ "learning_rate": 1e-05,
68
+ "loss": 0.5053,
69
+ "step": 120
70
+ },
71
+ {
72
+ "epoch": 3.75,
73
+ "eval_loss": 0.5857406258583069,
74
+ "eval_runtime": 552.994,
75
+ "eval_samples_per_second": 1.808,
76
+ "eval_steps_per_second": 1.808,
77
+ "eval_wer": 66.17833855533914,
78
+ "step": 120
79
+ },
80
+ {
81
+ "epoch": 4.375,
82
+ "grad_norm": 4.851699352264404,
83
+ "learning_rate": 1e-05,
84
+ "loss": 0.4369,
85
+ "step": 140
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 9.787827491760254,
90
+ "learning_rate": 1e-05,
91
+ "loss": 0.406,
92
+ "step": 160
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_loss": 0.5440071225166321,
97
+ "eval_runtime": 541.8179,
98
+ "eval_samples_per_second": 1.846,
99
+ "eval_steps_per_second": 1.846,
100
+ "eval_wer": 66.11059361503938,
101
+ "step": 160
102
+ },
103
+ {
104
+ "epoch": 5.625,
105
+ "grad_norm": 4.657484531402588,
106
+ "learning_rate": 1e-05,
107
+ "loss": 0.356,
108
+ "step": 180
109
+ },
110
+ {
111
+ "epoch": 6.25,
112
+ "grad_norm": 4.622303009033203,
113
+ "learning_rate": 1e-05,
114
+ "loss": 0.3236,
115
+ "step": 200
116
+ },
117
+ {
118
+ "epoch": 6.25,
119
+ "eval_loss": 0.5291295051574707,
120
+ "eval_runtime": 538.5029,
121
+ "eval_samples_per_second": 1.857,
122
+ "eval_steps_per_second": 1.857,
123
+ "eval_wer": 65.3061224489796,
124
+ "step": 200
125
+ },
126
+ {
127
+ "epoch": 6.25,
128
+ "step": 200,
129
+ "total_flos": 1.5401574531072e+17,
130
+ "train_loss": 0.7680728721618653,
131
+ "train_runtime": 3566.0921,
132
+ "train_samples_per_second": 1.795,
133
+ "train_steps_per_second": 0.056
134
+ }
135
+ ],
136
+ "logging_steps": 20,
137
+ "max_steps": 200,
138
+ "num_input_tokens_seen": 0,
139
+ "num_train_epochs": 7,
140
+ "save_steps": 40,
141
+ "stateful_callbacks": {
142
+ "TrainerControl": {
143
+ "args": {
144
+ "should_epoch_stop": false,
145
+ "should_evaluate": false,
146
+ "should_log": false,
147
+ "should_save": true,
148
+ "should_training_stop": true
149
+ },
150
+ "attributes": {}
151
+ }
152
+ },
153
+ "total_flos": 1.5401574531072e+17,
154
+ "train_batch_size": 32,
155
+ "trial_name": null,
156
+ "trial_params": null
157
+ }