PereLluis13 commited on
Commit
662c82b
1 Parent(s): 6b426ff

Training in progress, step 6000

Browse files
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.3033297657966614,
4
+ "eval_runtime": 395.7148,
5
+ "eval_samples": 4297,
6
+ "eval_samples_per_second": 10.859,
7
+ "eval_steps_per_second": 0.341,
8
+ "eval_wer": 0.19506011201512932,
9
+ "train_loss": 0.46717894900821066,
10
+ "train_runtime": 42700.8803,
11
+ "train_samples": 240334,
12
+ "train_samples_per_second": 16.885,
13
+ "train_steps_per_second": 0.132
14
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.3033297657966614,
4
+ "eval_runtime": 395.7148,
5
+ "eval_samples": 4297,
6
+ "eval_samples_per_second": 10.859,
7
+ "eval_steps_per_second": 0.341,
8
+ "eval_wer": 0.19506011201512932
9
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10b8e1e4605fca290d5637f77478cc5de89067a6e3dd236781ad3c3d70de68cb
3
  size 1262112241
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69b8c3e5a25929fe5518b2db2fc0b10d4c584f3b4511f4b9ec2bc19eb7f1d4a4
3
  size 1262112241
runs/Jan28_20-45-33_job-336a688f-553a-4e6e-83b3-ad5d10274b51/events.out.tfevents.1643412482.job-336a688f-553a-4e6e-83b3-ad5d10274b51.1189245.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c6b6d036c28f99ebb382382b8e2848d070749fe09cbc17a490b427cad92ce44
3
- size 6645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e29e7542794e6d9f43f9b278d28a04e7ff23e188392a22e6a077259111cbb7d
3
+ size 6999
runs/Jan28_20-45-33_job-336a688f-553a-4e6e-83b3-ad5d10274b51/events.out.tfevents.1643455581.job-336a688f-553a-4e6e-83b3-ad5d10274b51.1189245.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ad1ae5576bd3416a35b021fb919dad4e371ae9403e741e829e575ec56203db5
3
+ size 358
runs/Jan29_11-55-18_job-336a688f-553a-4e6e-83b3-ad5d10274b51/1643460077.0405679/events.out.tfevents.1643460077.job-336a688f-553a-4e6e-83b3-ad5d10274b51.1539029.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f8d5820deac48bf643fdd77bbb1bd465f636a90796b1c2628810308ca62348
3
+ size 4814
runs/Jan29_11-55-18_job-336a688f-553a-4e6e-83b3-ad5d10274b51/events.out.tfevents.1643460077.job-336a688f-553a-4e6e-83b3-ad5d10274b51.1539029.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7b03f34331375aed60c773aca2e4e4c67953313085ef60c3bd9c0aba81ffc68
3
+ size 5220
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}, {"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}]}
 
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}, {"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 ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.46717894900821066,
4
+ "train_runtime": 42700.8803,
5
+ "train_samples": 240334,
6
+ "train_samples_per_second": 16.885,
7
+ "train_steps_per_second": 0.132
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,190 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9996005858074826,
5
+ "global_step": 5631,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.09,
12
+ "learning_rate": 1.8712499999999997e-05,
13
+ "loss": 6.2099,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.09,
18
+ "eval_loss": 3.41253662109375,
19
+ "eval_runtime": 1358.074,
20
+ "eval_samples_per_second": 14.868,
21
+ "eval_steps_per_second": 0.465,
22
+ "eval_wer": 1.0,
23
+ "step": 500
24
+ },
25
+ {
26
+ "epoch": 0.18,
27
+ "learning_rate": 3.7462499999999996e-05,
28
+ "loss": 2.9961,
29
+ "step": 1000
30
+ },
31
+ {
32
+ "epoch": 0.18,
33
+ "eval_loss": 2.9223873615264893,
34
+ "eval_runtime": 1361.8836,
35
+ "eval_samples_per_second": 14.827,
36
+ "eval_steps_per_second": 0.463,
37
+ "eval_wer": 1.0,
38
+ "step": 1000
39
+ },
40
+ {
41
+ "epoch": 0.26,
42
+ "learning_rate": 5.62125e-05,
43
+ "loss": 2.2147,
44
+ "step": 1500
45
+ },
46
+ {
47
+ "epoch": 0.26,
48
+ "eval_loss": 0.6520791053771973,
49
+ "eval_runtime": 1355.9385,
50
+ "eval_samples_per_second": 14.892,
51
+ "eval_steps_per_second": 0.465,
52
+ "eval_wer": 0.5567824255052013,
53
+ "step": 1500
54
+ },
55
+ {
56
+ "epoch": 0.35,
57
+ "learning_rate": 7.49625e-05,
58
+ "loss": 1.3017,
59
+ "step": 2000
60
+ },
61
+ {
62
+ "epoch": 0.35,
63
+ "eval_loss": 0.31525641679763794,
64
+ "eval_runtime": 1371.0684,
65
+ "eval_samples_per_second": 14.727,
66
+ "eval_steps_per_second": 0.46,
67
+ "eval_wer": 0.27607269814249236,
68
+ "step": 2000
69
+ },
70
+ {
71
+ "epoch": 0.44,
72
+ "learning_rate": 7.431581352833637e-05,
73
+ "loss": 1.1196,
74
+ "step": 2500
75
+ },
76
+ {
77
+ "epoch": 0.44,
78
+ "eval_loss": 0.24444133043289185,
79
+ "eval_runtime": 1363.4869,
80
+ "eval_samples_per_second": 14.809,
81
+ "eval_steps_per_second": 0.463,
82
+ "eval_wer": 0.23673497683411066,
83
+ "step": 2500
84
+ },
85
+ {
86
+ "epoch": 0.53,
87
+ "learning_rate": 7.363162705667275e-05,
88
+ "loss": 1.0712,
89
+ "step": 3000
90
+ },
91
+ {
92
+ "epoch": 0.53,
93
+ "eval_loss": 0.23236490786075592,
94
+ "eval_runtime": 1368.4487,
95
+ "eval_samples_per_second": 14.755,
96
+ "eval_steps_per_second": 0.461,
97
+ "eval_wer": 0.21321861436015543,
98
+ "step": 3000
99
+ },
100
+ {
101
+ "epoch": 0.62,
102
+ "learning_rate": 7.294606946983546e-05,
103
+ "loss": 1.052,
104
+ "step": 3500
105
+ },
106
+ {
107
+ "epoch": 0.62,
108
+ "eval_loss": 0.21734564006328583,
109
+ "eval_runtime": 1358.6503,
110
+ "eval_samples_per_second": 14.862,
111
+ "eval_steps_per_second": 0.464,
112
+ "eval_wer": 0.20317428528513493,
113
+ "step": 3500
114
+ },
115
+ {
116
+ "epoch": 2.13,
117
+ "learning_rate": 3.375103277334068e-05,
118
+ "loss": 1.2813,
119
+ "step": 4000
120
+ },
121
+ {
122
+ "epoch": 2.13,
123
+ "eval_loss": 0.332599401473999,
124
+ "eval_runtime": 393.989,
125
+ "eval_samples_per_second": 10.906,
126
+ "eval_steps_per_second": 0.343,
127
+ "eval_wer": 0.20989847979467358,
128
+ "step": 4000
129
+ },
130
+ {
131
+ "epoch": 2.4,
132
+ "learning_rate": 2.3423299366565682e-05,
133
+ "loss": 1.2365,
134
+ "step": 4500
135
+ },
136
+ {
137
+ "epoch": 2.4,
138
+ "eval_loss": 0.3223731815814972,
139
+ "eval_runtime": 391.7507,
140
+ "eval_samples_per_second": 10.969,
141
+ "eval_steps_per_second": 0.345,
142
+ "eval_wer": 0.2003283560376986,
143
+ "step": 4500
144
+ },
145
+ {
146
+ "epoch": 2.66,
147
+ "learning_rate": 1.309556595979069e-05,
148
+ "loss": 1.2193,
149
+ "step": 5000
150
+ },
151
+ {
152
+ "epoch": 2.66,
153
+ "eval_loss": 0.31981074810028076,
154
+ "eval_runtime": 402.4439,
155
+ "eval_samples_per_second": 10.677,
156
+ "eval_steps_per_second": 0.335,
157
+ "eval_wer": 0.19565239980464894,
158
+ "step": 5000
159
+ },
160
+ {
161
+ "epoch": 2.93,
162
+ "learning_rate": 2.767832553015698e-06,
163
+ "loss": 1.2072,
164
+ "step": 5500
165
+ },
166
+ {
167
+ "epoch": 2.93,
168
+ "eval_loss": 0.3063456118106842,
169
+ "eval_runtime": 396.6525,
170
+ "eval_samples_per_second": 10.833,
171
+ "eval_steps_per_second": 0.34,
172
+ "eval_wer": 0.19327285763271923,
173
+ "step": 5500
174
+ },
175
+ {
176
+ "epoch": 3.0,
177
+ "step": 5631,
178
+ "total_flos": 1.4549289807228204e+20,
179
+ "train_loss": 0.46717894900821066,
180
+ "train_runtime": 42700.8803,
181
+ "train_samples_per_second": 16.885,
182
+ "train_steps_per_second": 0.132
183
+ }
184
+ ],
185
+ "max_steps": 5631,
186
+ "num_train_epochs": 3,
187
+ "total_flos": 1.4549289807228204e+20,
188
+ "trial_name": null,
189
+ "trial_params": null
190
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:900730258ef5ba01c3771eb89400d63447160b6a533e2bc89e44d21af9e331f2
3
  size 3055
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5c09474639eff781a9fbbd58d81fc04a95748d863d0d33f663b0592e8c64a21
3
  size 3055