sanchit-gandhi HF staff commited on
Commit
30cf64e
β€’
1 Parent(s): c81eede

update model card README.md

Browse files
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model was trained from scratch on the xtreme_s dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.6425
21
  - Bleu: 0.0000
 
22
 
23
  ## Model description
24
 
@@ -37,7 +37,7 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 0.00012335092351490598
41
  - train_batch_size: 8
42
  - eval_batch_size: 8
43
  - seed: 42
@@ -51,27 +51,27 @@ The following hyperparameters were used during training:
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Bleu |
55
- |:-------------:|:-----:|:----:|:---------------:|:------:|
56
- | 2.8303 | 0.15 | 500 | 4.9238 | 0.0 |
57
- | 2.4062 | 0.31 | 1000 | 4.4017 | 0.0 |
58
- | 1.9171 | 0.46 | 1500 | 3.6431 | 0.0000 |
59
- | 1.4558 | 0.62 | 2000 | 2.8292 | 0.0000 |
60
- | 1.2393 | 0.77 | 2500 | 2.3704 | 0.0000 |
61
- | 1.3315 | 0.93 | 3000 | 2.3101 | 0.0000 |
62
- | 1.8476 | 1.08 | 3500 | 1.9936 | 0.0000 |
63
- | 1.683 | 1.23 | 4000 | 1.9308 | 0.0000 |
64
- | 1.8298 | 1.39 | 4500 | 1.8817 | 0.0000 |
65
- | 1.5955 | 1.54 | 5000 | 1.8171 | 0.0000 |
66
- | 1.6288 | 1.7 | 5500 | 1.7821 | 0.0000 |
67
- | 1.4107 | 1.85 | 6000 | 1.7170 | 0.0000 |
68
- | 1.0363 | 2.01 | 6500 | 1.7419 | 0.0000 |
69
- | 0.9667 | 2.16 | 7000 | 1.7309 | 0.0000 |
70
- | 0.9147 | 2.31 | 7500 | 1.7244 | 0.0000 |
71
- | 1.1975 | 2.47 | 8000 | 1.6716 | 0.0000 |
72
- | 0.9071 | 2.62 | 8500 | 1.6886 | 0.0000 |
73
- | 0.9735 | 2.78 | 9000 | 1.6609 | 0.0000 |
74
- | 0.908 | 2.93 | 9500 | 1.6425 | 0.0000 |
75
 
76
 
77
  ### Framework versions
 
17
 
18
  This model was trained from scratch on the xtreme_s dataset.
19
  It achieves the following results on the evaluation set:
 
20
  - Bleu: 0.0000
21
+ - Loss: 1.6425
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 0.0004100464310609422
41
  - train_batch_size: 8
42
  - eval_batch_size: 8
43
  - seed: 42
 
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Bleu | Validation Loss |
55
+ |:-------------:|:-----:|:----:|:------:|:---------------:|
56
+ | 2.8303 | 0.15 | 500 | 0.0 | 4.9238 |
57
+ | 2.4062 | 0.31 | 1000 | 0.0 | 4.4017 |
58
+ | 1.9171 | 0.46 | 1500 | 0.0000 | 3.6431 |
59
+ | 1.4558 | 0.62 | 2000 | 0.0000 | 2.8292 |
60
+ | 1.2393 | 0.77 | 2500 | 0.0000 | 2.3704 |
61
+ | 1.3315 | 0.93 | 3000 | 0.0000 | 2.3101 |
62
+ | 1.8476 | 1.08 | 3500 | 0.0000 | 1.9936 |
63
+ | 1.683 | 1.23 | 4000 | 0.0000 | 1.9308 |
64
+ | 1.8298 | 1.39 | 4500 | 0.0000 | 1.8817 |
65
+ | 1.5955 | 1.54 | 5000 | 0.0000 | 1.8171 |
66
+ | 1.6288 | 1.7 | 5500 | 0.0000 | 1.7821 |
67
+ | 1.4107 | 1.85 | 6000 | 0.0000 | 1.7170 |
68
+ | 1.0363 | 2.01 | 6500 | 0.0000 | 1.7419 |
69
+ | 0.9667 | 2.16 | 7000 | 0.0000 | 1.7309 |
70
+ | 0.9147 | 2.31 | 7500 | 0.0000 | 1.7244 |
71
+ | 1.1975 | 2.47 | 8000 | 0.0000 | 1.6716 |
72
+ | 0.9071 | 2.62 | 8500 | 0.0000 | 1.6886 |
73
+ | 0.9735 | 2.78 | 9000 | 0.0000 | 1.6609 |
74
+ | 0.908 | 2.93 | 9500 | 0.0000 | 1.6425 |
75
 
76
 
77
  ### Framework versions
wandb/run-20220505_165612-npwlqyuz/files/output.log CHANGED
@@ -26,3 +26,19 @@ Feature extractor saved in ./preprocessor_config.json
26
  Saving model checkpoint to ./
27
  Configuration saved in ./config.json
28
  Model weights saved in ./pytorch_model.bin
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
26
  Saving model checkpoint to ./
27
  Configuration saved in ./config.json
28
  Model weights saved in ./pytorch_model.bin
29
+ Feature extractor saved in ./preprocessor_config.json
30
+ Upload file wandb/run-20220504_142129-w4rlzz90/run-w4rlzz90.wandb: 0%| | 32.0k/971M [00:00<?, ?B/s]
31
+ Upload file wandb/run-20220504_142129-w4rlzz90/logs/debug-internal.log: 0%| | 32.0k/20.5M [00:00<?, ?B/s]
32
+ Upload file runs/May05_16-55-19_sanchit--v100/events.out.tfevents.1651769771.sanchit--v100.69604.0: 100%|β–ˆ| 9.97k/9.97k
33
+ Upload file runs/May05_16-55-19_sanchit--v100/1651769771.7857685/events.out.tfevents.1651769771.sanchit--v100.69604.1: 1
34
+ Upload file training_args.bin: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 3.17k/3.17k [00:00<?, ?B/s]
35
+
36
+
37
+ Upload file wandb/run-20220504_142129-w4rlzz90/files/output.log: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 10.7M/10.7M [00:13<00:00, 8.74MB/s]
38
+ 05/05/2022 16:58:12 - WARNING - huggingface_hub.repository - To https://huggingface.co/sanchit-gandhi/xtreme_s_xlsr_2_bart_covost2_fr_en_2
39
+ Upload file runs/May05_16-55-19_sanchit--v100/events.out.tfevents.1651769771.sanchit--v100.69604.0: 100%|β–ˆ| 9.97k/9.97k
40
+ Upload file runs/May05_16-55-19_sanchit--v100/1651769771.7857685/events.out.tfevents.1651769771.sanchit--v100.69604.1: 1
41
+ Upload file training_args.bin: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 3.17k/3.17k [00:54<?, ?B/s]
42
+ Upload file wandb/run-20220504_142129-w4rlzz90/files/output.log: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 10.7M/10.7M [00:54<00:00, 206kB/s]
43
+ Upload file runs/May05_16-55-19_sanchit--v100/1651769771.7857685/events.out.tfevents.1651769771.sanchit--v100.69604.1: 1
44
+ Upload file training_args.bin: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 3.17k/3.17k [00:54<?, ?B/s]
wandb/run-20220505_165612-npwlqyuz/logs/debug-internal.log CHANGED
@@ -54,3 +54,19 @@
54
  2022-05-05 16:57:01,445 DEBUG HandlerThread:69718 [handler.py:handle_request():131] handle_request: stop_status
55
  2022-05-05 16:57:01,445 DEBUG SenderThread:69718 [sender.py:send_request():249] send_request: stop_status
56
  2022-05-05 16:57:14,261 DEBUG SenderThread:69718 [sender.py:send():235] send: stats
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
  2022-05-05 16:57:01,445 DEBUG HandlerThread:69718 [handler.py:handle_request():131] handle_request: stop_status
55
  2022-05-05 16:57:01,445 DEBUG SenderThread:69718 [sender.py:send_request():249] send_request: stop_status
56
  2022-05-05 16:57:14,261 DEBUG SenderThread:69718 [sender.py:send():235] send: stats
57
+ 2022-05-05 16:57:16,488 DEBUG HandlerThread:69718 [handler.py:handle_request():131] handle_request: stop_status
58
+ 2022-05-05 16:57:16,489 DEBUG SenderThread:69718 [sender.py:send_request():249] send_request: stop_status
59
+ 2022-05-05 16:57:20,327 INFO Thread-8 :69718 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en_2/wandb/run-20220505_165612-npwlqyuz/files/output.log
60
+ 2022-05-05 16:57:22,328 INFO Thread-8 :69718 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en_2/wandb/run-20220505_165612-npwlqyuz/files/output.log
61
+ 2022-05-05 16:57:31,525 DEBUG HandlerThread:69718 [handler.py:handle_request():131] handle_request: stop_status
62
+ 2022-05-05 16:57:31,526 DEBUG SenderThread:69718 [sender.py:send_request():249] send_request: stop_status
63
+ 2022-05-05 16:57:34,332 INFO Thread-8 :69718 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en_2/wandb/run-20220505_165612-npwlqyuz/files/output.log
64
+ 2022-05-05 16:57:44,628 DEBUG SenderThread:69718 [sender.py:send():235] send: stats
65
+ 2022-05-05 16:57:46,563 DEBUG HandlerThread:69718 [handler.py:handle_request():131] handle_request: stop_status
66
+ 2022-05-05 16:57:46,564 DEBUG SenderThread:69718 [sender.py:send_request():249] send_request: stop_status
67
+ 2022-05-05 16:58:01,607 DEBUG HandlerThread:69718 [handler.py:handle_request():131] handle_request: stop_status
68
+ 2022-05-05 16:58:01,608 DEBUG SenderThread:69718 [sender.py:send_request():249] send_request: stop_status
69
+ 2022-05-05 16:58:14,348 INFO Thread-8 :69718 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en_2/wandb/run-20220505_165612-npwlqyuz/files/output.log
70
+ 2022-05-05 16:58:14,989 DEBUG SenderThread:69718 [sender.py:send():235] send: stats
71
+ 2022-05-05 16:58:16,646 DEBUG HandlerThread:69718 [handler.py:handle_request():131] handle_request: stop_status
72
+ 2022-05-05 16:58:16,646 DEBUG SenderThread:69718 [sender.py:send_request():249] send_request: stop_status
wandb/run-20220505_165612-npwlqyuz/run-npwlqyuz.wandb CHANGED
Binary files a/wandb/run-20220505_165612-npwlqyuz/run-npwlqyuz.wandb and b/wandb/run-20220505_165612-npwlqyuz/run-npwlqyuz.wandb differ