nouamanetazi HF staff commited on
Commit
61b2101
1 Parent(s): eb6ce44

Model save

Browse files
.ipynb_checkpoints/tokenizer_config-checkpoint.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./wav2vec2-xls-r-300m-ar", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
.ipynb_checkpoints/train_results-checkpoint.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "total_flos": 1.3476444758728704e+17,
4
+ "train_loss": 16.66825189590454,
5
+ "train_runtime": 91.9274,
6
+ "train_samples": 128,
7
+ "train_samples_per_second": 6.962,
8
+ "train_steps_per_second": 0.109
9
+ }
all_results.json CHANGED
@@ -7,9 +7,9 @@
7
  "eval_steps_per_second": 0.334,
8
  "eval_wer": 1.0,
9
  "total_flos": 1.3476444758728704e+17,
10
- "train_loss": 19.56191415786743,
11
- "train_runtime": 92.9692,
12
  "train_samples": 128,
13
- "train_samples_per_second": 6.884,
14
- "train_steps_per_second": 0.108
15
  }
 
7
  "eval_steps_per_second": 0.334,
8
  "eval_wer": 1.0,
9
  "total_flos": 1.3476444758728704e+17,
10
+ "train_loss": 16.66825189590454,
11
+ "train_runtime": 91.9274,
12
  "train_samples": 128,
13
+ "train_samples_per_second": 6.962,
14
+ "train_steps_per_second": 0.109
15
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ea93def4f37206b423024351165f6f76fb31abde5bd5c8aa0c1691f50e4ca3b
3
  size 1262067185
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffac37d2a17fb457b11df915b6fb3a959357616b3a8f9bdd9aa20fc3083c8eb9
3
  size 1262067185
special_tokens_map.json CHANGED
@@ -1 +1 @@
1
- {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 5.0,
3
  "total_flos": 1.3476444758728704e+17,
4
- "train_loss": 19.56191415786743,
5
- "train_runtime": 92.9692,
6
  "train_samples": 128,
7
- "train_samples_per_second": 6.884,
8
- "train_steps_per_second": 0.108
9
  }
 
1
  {
2
  "epoch": 5.0,
3
  "total_flos": 1.3476444758728704e+17,
4
+ "train_loss": 16.66825189590454,
5
+ "train_runtime": 91.9274,
6
  "train_samples": 128,
7
+ "train_samples_per_second": 6.962,
8
+ "train_steps_per_second": 0.109
9
  }
trainer_state.json CHANGED
@@ -10,150 +10,150 @@
10
  {
11
  "epoch": 0.5,
12
  "learning_rate": 7.5e-05,
13
- "loss": 22.283,
14
  "step": 1
15
  },
16
  {
17
  "epoch": 0.5,
18
- "eval_loss": 38.53455352783203,
19
- "eval_runtime": 5.6686,
20
- "eval_samples_per_second": 22.581,
21
- "eval_steps_per_second": 0.353,
22
  "eval_wer": 1.0,
23
  "step": 1
24
  },
25
  {
26
  "epoch": 1.0,
27
  "learning_rate": 7.5e-05,
28
- "loss": 22.622,
29
  "step": 2
30
  },
31
  {
32
  "epoch": 1.0,
33
- "eval_loss": 38.53455352783203,
34
- "eval_runtime": 5.4852,
35
- "eval_samples_per_second": 23.336,
36
- "eval_steps_per_second": 0.365,
37
  "eval_wer": 1.0,
38
  "step": 2
39
  },
40
  {
41
  "epoch": 1.5,
42
  "learning_rate": 6.75e-05,
43
- "loss": 23.0656,
44
  "step": 3
45
  },
46
  {
47
  "epoch": 1.5,
48
- "eval_loss": 37.73825454711914,
49
- "eval_runtime": 5.4328,
50
- "eval_samples_per_second": 23.561,
51
- "eval_steps_per_second": 0.368,
52
  "eval_wer": 1.0,
53
  "step": 3
54
  },
55
  {
56
  "epoch": 2.0,
57
- "learning_rate": 6.75e-05,
58
- "loss": 20.8353,
59
  "step": 4
60
  },
61
  {
62
  "epoch": 2.0,
63
- "eval_loss": 37.73825454711914,
64
- "eval_runtime": 5.7103,
65
- "eval_samples_per_second": 22.416,
66
- "eval_steps_per_second": 0.35,
67
  "eval_wer": 1.0,
68
  "step": 4
69
  },
70
  {
71
  "epoch": 2.5,
72
  "learning_rate": 5.9999999999999995e-05,
73
- "loss": 21.4977,
74
  "step": 5
75
  },
76
  {
77
  "epoch": 2.5,
78
- "eval_loss": 36.794700622558594,
79
- "eval_runtime": 5.4096,
80
- "eval_samples_per_second": 23.661,
81
- "eval_steps_per_second": 0.37,
82
  "eval_wer": 1.0,
83
  "step": 5
84
  },
85
  {
86
  "epoch": 3.0,
87
  "learning_rate": 5.2499999999999995e-05,
88
- "loss": 20.1685,
89
  "step": 6
90
  },
91
  {
92
  "epoch": 3.0,
93
- "eval_loss": 35.34020233154297,
94
- "eval_runtime": 5.6574,
95
- "eval_samples_per_second": 22.625,
96
- "eval_steps_per_second": 0.354,
97
  "eval_wer": 1.0,
98
  "step": 6
99
  },
100
  {
101
  "epoch": 3.5,
102
  "learning_rate": 4.4999999999999996e-05,
103
- "loss": 19.3566,
104
  "step": 7
105
  },
106
  {
107
  "epoch": 3.5,
108
- "eval_loss": 33.572959899902344,
109
- "eval_runtime": 5.6556,
110
- "eval_samples_per_second": 22.632,
111
- "eval_steps_per_second": 0.354,
112
  "eval_wer": 1.0,
113
  "step": 7
114
  },
115
  {
116
  "epoch": 4.0,
117
  "learning_rate": 3.75e-05,
118
- "loss": 15.8992,
119
  "step": 8
120
  },
121
  {
122
  "epoch": 4.0,
123
- "eval_loss": 30.588499069213867,
124
- "eval_runtime": 5.3488,
125
- "eval_samples_per_second": 23.93,
126
- "eval_steps_per_second": 0.374,
127
  "eval_wer": 1.0,
128
  "step": 8
129
  },
130
  {
131
  "epoch": 4.5,
132
  "learning_rate": 2.9999999999999997e-05,
133
- "loss": 15.0607,
134
  "step": 9
135
  },
136
  {
137
  "epoch": 4.5,
138
- "eval_loss": 27.82217788696289,
139
- "eval_runtime": 5.6203,
140
- "eval_samples_per_second": 22.774,
141
- "eval_steps_per_second": 0.356,
142
  "eval_wer": 1.0,
143
  "step": 9
144
  },
145
  {
146
  "epoch": 5.0,
147
  "learning_rate": 2.2499999999999998e-05,
148
- "loss": 14.8305,
149
  "step": 10
150
  },
151
  {
152
  "epoch": 5.0,
153
- "eval_loss": 25.9698429107666,
154
- "eval_runtime": 5.6638,
155
- "eval_samples_per_second": 22.599,
156
- "eval_steps_per_second": 0.353,
157
  "eval_wer": 1.0,
158
  "step": 10
159
  },
@@ -161,10 +161,10 @@
161
  "epoch": 5.0,
162
  "step": 10,
163
  "total_flos": 1.3476444758728704e+17,
164
- "train_loss": 19.56191415786743,
165
- "train_runtime": 92.9692,
166
- "train_samples_per_second": 6.884,
167
- "train_steps_per_second": 0.108
168
  }
169
  ],
170
  "max_steps": 10,
 
10
  {
11
  "epoch": 0.5,
12
  "learning_rate": 7.5e-05,
13
+ "loss": 18.7839,
14
  "step": 1
15
  },
16
  {
17
  "epoch": 0.5,
18
+ "eval_loss": 32.55470657348633,
19
+ "eval_runtime": 5.5933,
20
+ "eval_samples_per_second": 22.884,
21
+ "eval_steps_per_second": 0.358,
22
  "eval_wer": 1.0,
23
  "step": 1
24
  },
25
  {
26
  "epoch": 1.0,
27
  "learning_rate": 7.5e-05,
28
+ "loss": 19.4045,
29
  "step": 2
30
  },
31
  {
32
  "epoch": 1.0,
33
+ "eval_loss": 32.55470657348633,
34
+ "eval_runtime": 5.6123,
35
+ "eval_samples_per_second": 22.807,
36
+ "eval_steps_per_second": 0.356,
37
  "eval_wer": 1.0,
38
  "step": 2
39
  },
40
  {
41
  "epoch": 1.5,
42
  "learning_rate": 6.75e-05,
43
+ "loss": 19.6279,
44
  "step": 3
45
  },
46
  {
47
  "epoch": 1.5,
48
+ "eval_loss": 31.884950637817383,
49
+ "eval_runtime": 5.4543,
50
+ "eval_samples_per_second": 23.468,
51
+ "eval_steps_per_second": 0.367,
52
  "eval_wer": 1.0,
53
  "step": 3
54
  },
55
  {
56
  "epoch": 2.0,
57
+ "learning_rate": 5.9999999999999995e-05,
58
+ "loss": 17.7216,
59
  "step": 4
60
  },
61
  {
62
  "epoch": 2.0,
63
+ "eval_loss": 31.10820960998535,
64
+ "eval_runtime": 5.4982,
65
+ "eval_samples_per_second": 23.28,
66
+ "eval_steps_per_second": 0.364,
67
  "eval_wer": 1.0,
68
  "step": 4
69
  },
70
  {
71
  "epoch": 2.5,
72
  "learning_rate": 5.9999999999999995e-05,
73
+ "loss": 17.3103,
74
  "step": 5
75
  },
76
  {
77
  "epoch": 2.5,
78
+ "eval_loss": 31.10820960998535,
79
+ "eval_runtime": 5.9789,
80
+ "eval_samples_per_second": 21.409,
81
+ "eval_steps_per_second": 0.335,
82
  "eval_wer": 1.0,
83
  "step": 5
84
  },
85
  {
86
  "epoch": 3.0,
87
  "learning_rate": 5.2499999999999995e-05,
88
+ "loss": 17.2026,
89
  "step": 6
90
  },
91
  {
92
  "epoch": 3.0,
93
+ "eval_loss": 29.966575622558594,
94
+ "eval_runtime": 5.3861,
95
+ "eval_samples_per_second": 23.765,
96
+ "eval_steps_per_second": 0.371,
97
  "eval_wer": 1.0,
98
  "step": 6
99
  },
100
  {
101
  "epoch": 3.5,
102
  "learning_rate": 4.4999999999999996e-05,
103
+ "loss": 16.7911,
104
  "step": 7
105
  },
106
  {
107
  "epoch": 3.5,
108
+ "eval_loss": 28.54442596435547,
109
+ "eval_runtime": 5.434,
110
+ "eval_samples_per_second": 23.555,
111
+ "eval_steps_per_second": 0.368,
112
  "eval_wer": 1.0,
113
  "step": 7
114
  },
115
  {
116
  "epoch": 4.0,
117
  "learning_rate": 3.75e-05,
118
+ "loss": 13.7364,
119
  "step": 8
120
  },
121
  {
122
  "epoch": 4.0,
123
+ "eval_loss": 25.79315185546875,
124
+ "eval_runtime": 5.4455,
125
+ "eval_samples_per_second": 23.506,
126
+ "eval_steps_per_second": 0.367,
127
  "eval_wer": 1.0,
128
  "step": 8
129
  },
130
  {
131
  "epoch": 4.5,
132
  "learning_rate": 2.9999999999999997e-05,
133
+ "loss": 13.1602,
134
  "step": 9
135
  },
136
  {
137
  "epoch": 4.5,
138
+ "eval_loss": 23.46338653564453,
139
+ "eval_runtime": 5.3714,
140
+ "eval_samples_per_second": 23.83,
141
+ "eval_steps_per_second": 0.372,
142
  "eval_wer": 1.0,
143
  "step": 9
144
  },
145
  {
146
  "epoch": 5.0,
147
  "learning_rate": 2.2499999999999998e-05,
148
+ "loss": 12.9439,
149
  "step": 10
150
  },
151
  {
152
  "epoch": 5.0,
153
+ "eval_loss": 21.93878936767578,
154
+ "eval_runtime": 5.4116,
155
+ "eval_samples_per_second": 23.653,
156
+ "eval_steps_per_second": 0.37,
157
  "eval_wer": 1.0,
158
  "step": 10
159
  },
 
161
  "epoch": 5.0,
162
  "step": 10,
163
  "total_flos": 1.3476444758728704e+17,
164
+ "train_loss": 16.66825189590454,
165
+ "train_runtime": 91.9274,
166
+ "train_samples_per_second": 6.962,
167
+ "train_steps_per_second": 0.109
168
  }
169
  ],
170
  "max_steps": 10,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:205b839c6738065c780db23902fe5de7ab8a5a6745c332ab60e9b1d434f7d4e6
3
  size 3055
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:403aa5248b80fb24657e0dfbc1021fe9ec7e35859e5e11e0d7f4b5c307315ae2
3
  size 3055