sanchit-gandhi HF staff commited on
Commit
ebabff2
1 Parent(s): 3e58079

End of training

Browse files
all_results.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "epoch": 3.0,
3
  "eval_loss": 18.79399871826172,
4
- "eval_runtime": 1070.4999,
5
  "eval_samples": 2642,
6
- "eval_samples_per_second": 2.468,
7
- "eval_steps_per_second": 0.309,
8
  "eval_wer": 1.0,
9
  "train_loss": 5.609615023672491,
10
- "train_runtime": 24845.7878,
11
  "train_samples": 28538,
12
- "train_samples_per_second": 3.446,
13
- "train_steps_per_second": 0.215
14
  }
 
1
  {
2
  "epoch": 3.0,
3
  "eval_loss": 18.79399871826172,
4
+ "eval_runtime": 1047.771,
5
  "eval_samples": 2642,
6
+ "eval_samples_per_second": 2.522,
7
+ "eval_steps_per_second": 0.316,
8
  "eval_wer": 1.0,
9
  "train_loss": 5.609615023672491,
10
+ "train_runtime": 24667.9377,
11
  "train_samples": 28538,
12
+ "train_samples_per_second": 3.471,
13
+ "train_steps_per_second": 0.217
14
  }
eval_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 3.0,
3
  "eval_loss": 18.79399871826172,
4
- "eval_runtime": 1070.4999,
5
  "eval_samples": 2642,
6
- "eval_samples_per_second": 2.468,
7
- "eval_steps_per_second": 0.309,
8
  "eval_wer": 1.0
9
  }
 
1
  {
2
  "epoch": 3.0,
3
  "eval_loss": 18.79399871826172,
4
+ "eval_runtime": 1047.771,
5
  "eval_samples": 2642,
6
+ "eval_samples_per_second": 2.522,
7
+ "eval_steps_per_second": 0.316,
8
  "eval_wer": 1.0
9
  }
runs/Feb21_17-57-39_sanchit--v100/events.out.tfevents.1645492095.sanchit--v100.90840.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f42088e23202217784c98094e222584ea0d3338f6c6bf0987d271ac2cc3db5da
3
+ size 358
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 3.0,
3
  "train_loss": 5.609615023672491,
4
- "train_runtime": 24845.7878,
5
  "train_samples": 28538,
6
- "train_samples_per_second": 3.446,
7
- "train_steps_per_second": 0.215
8
  }
 
1
  {
2
  "epoch": 3.0,
3
  "train_loss": 5.609615023672491,
4
+ "train_runtime": 24667.9377,
5
  "train_samples": 28538,
6
+ "train_samples_per_second": 3.471,
7
+ "train_steps_per_second": 0.217
8
  }
trainer_state.json CHANGED
@@ -3010,9 +3010,9 @@
3010
  {
3011
  "epoch": 0.28,
3012
  "eval_loss": 9.04012393951416,
3013
- "eval_runtime": 866.6614,
3014
- "eval_samples_per_second": 3.048,
3015
- "eval_steps_per_second": 0.382,
3016
  "eval_wer": 1.0119595398651329,
3017
  "step": 500
3018
  },
@@ -6019,9 +6019,9 @@
6019
  {
6020
  "epoch": 0.56,
6021
  "eval_loss": 9.319939613342285,
6022
- "eval_runtime": 865.2484,
6023
- "eval_samples_per_second": 3.053,
6024
- "eval_steps_per_second": 0.383,
6025
  "eval_wer": 1.0,
6026
  "step": 1000
6027
  },
@@ -9028,9 +9028,9 @@
9028
  {
9029
  "epoch": 0.84,
9030
  "eval_loss": 8.443438529968262,
9031
- "eval_runtime": 869.1873,
9032
- "eval_samples_per_second": 3.04,
9033
- "eval_steps_per_second": 0.381,
9034
  "eval_wer": 1.4562673542245141,
9035
  "step": 1500
9036
  },
@@ -12037,9 +12037,9 @@
12037
  {
12038
  "epoch": 1.12,
12039
  "eval_loss": 15.180464744567871,
12040
- "eval_runtime": 876.5269,
12041
- "eval_samples_per_second": 3.014,
12042
- "eval_steps_per_second": 0.378,
12043
  "eval_wer": 0.9999801666005553,
12044
  "step": 2000
12045
  },
@@ -15046,9 +15046,9 @@
15046
  {
15047
  "epoch": 1.4,
15048
  "eval_loss": 15.79842472076416,
15049
- "eval_runtime": 873.0125,
15050
- "eval_samples_per_second": 3.026,
15051
- "eval_steps_per_second": 0.379,
15052
  "eval_wer": 1.0020825069416899,
15053
  "step": 2500
15054
  },
@@ -18055,9 +18055,9 @@
18055
  {
18056
  "epoch": 1.68,
18057
  "eval_loss": 18.492834091186523,
18058
- "eval_runtime": 868.8561,
18059
- "eval_samples_per_second": 3.041,
18060
- "eval_steps_per_second": 0.381,
18061
  "eval_wer": 1.0,
18062
  "step": 3000
18063
  },
@@ -21064,9 +21064,9 @@
21064
  {
21065
  "epoch": 1.96,
21066
  "eval_loss": 17.48856544494629,
21067
- "eval_runtime": 871.6792,
21068
- "eval_samples_per_second": 3.031,
21069
- "eval_steps_per_second": 0.38,
21070
  "eval_wer": 0.9999801666005553,
21071
  "step": 3500
21072
  },
@@ -24073,9 +24073,9 @@
24073
  {
24074
  "epoch": 2.24,
24075
  "eval_loss": 18.945817947387695,
24076
- "eval_runtime": 896.893,
24077
- "eval_samples_per_second": 2.946,
24078
- "eval_steps_per_second": 0.369,
24079
  "eval_wer": 1.0,
24080
  "step": 4000
24081
  },
@@ -27082,9 +27082,9 @@
27082
  {
27083
  "epoch": 2.52,
27084
  "eval_loss": 18.279401779174805,
27085
- "eval_runtime": 900.0015,
27086
- "eval_samples_per_second": 2.936,
27087
- "eval_steps_per_second": 0.368,
27088
  "eval_wer": 1.0005553351844507,
27089
  "step": 4500
27090
  },
@@ -30091,9 +30091,9 @@
30091
  {
30092
  "epoch": 2.8,
30093
  "eval_loss": 18.789825439453125,
30094
- "eval_runtime": 902.298,
30095
- "eval_samples_per_second": 2.928,
30096
- "eval_steps_per_second": 0.367,
30097
  "eval_wer": 1.0,
30098
  "step": 5000
30099
  },
@@ -32214,9 +32214,9 @@
32214
  "step": 5352,
32215
  "total_flos": 0.0,
32216
  "train_loss": 5.609615023672491,
32217
- "train_runtime": 24845.7878,
32218
- "train_samples_per_second": 3.446,
32219
- "train_steps_per_second": 0.215
32220
  }
32221
  ],
32222
  "max_steps": 5352,
 
3010
  {
3011
  "epoch": 0.28,
3012
  "eval_loss": 9.04012393951416,
3013
+ "eval_runtime": 872.8535,
3014
+ "eval_samples_per_second": 3.027,
3015
+ "eval_steps_per_second": 0.379,
3016
  "eval_wer": 1.0119595398651329,
3017
  "step": 500
3018
  },
 
6019
  {
6020
  "epoch": 0.56,
6021
  "eval_loss": 9.319939613342285,
6022
+ "eval_runtime": 873.1949,
6023
+ "eval_samples_per_second": 3.026,
6024
+ "eval_steps_per_second": 0.379,
6025
  "eval_wer": 1.0,
6026
  "step": 1000
6027
  },
 
9028
  {
9029
  "epoch": 0.84,
9030
  "eval_loss": 8.443438529968262,
9031
+ "eval_runtime": 873.0258,
9032
+ "eval_samples_per_second": 3.026,
9033
+ "eval_steps_per_second": 0.379,
9034
  "eval_wer": 1.4562673542245141,
9035
  "step": 1500
9036
  },
 
12037
  {
12038
  "epoch": 1.12,
12039
  "eval_loss": 15.180464744567871,
12040
+ "eval_runtime": 877.3652,
12041
+ "eval_samples_per_second": 3.011,
12042
+ "eval_steps_per_second": 0.377,
12043
  "eval_wer": 0.9999801666005553,
12044
  "step": 2000
12045
  },
 
15046
  {
15047
  "epoch": 1.4,
15048
  "eval_loss": 15.79842472076416,
15049
+ "eval_runtime": 879.1328,
15050
+ "eval_samples_per_second": 3.005,
15051
+ "eval_steps_per_second": 0.377,
15052
  "eval_wer": 1.0020825069416899,
15053
  "step": 2500
15054
  },
 
18055
  {
18056
  "epoch": 1.68,
18057
  "eval_loss": 18.492834091186523,
18058
+ "eval_runtime": 877.1195,
18059
+ "eval_samples_per_second": 3.012,
18060
+ "eval_steps_per_second": 0.377,
18061
  "eval_wer": 1.0,
18062
  "step": 3000
18063
  },
 
21064
  {
21065
  "epoch": 1.96,
21066
  "eval_loss": 17.48856544494629,
21067
+ "eval_runtime": 876.0525,
21068
+ "eval_samples_per_second": 3.016,
21069
+ "eval_steps_per_second": 0.378,
21070
  "eval_wer": 0.9999801666005553,
21071
  "step": 3500
21072
  },
 
24073
  {
24074
  "epoch": 2.24,
24075
  "eval_loss": 18.945817947387695,
24076
+ "eval_runtime": 874.0614,
24077
+ "eval_samples_per_second": 3.023,
24078
+ "eval_steps_per_second": 0.379,
24079
  "eval_wer": 1.0,
24080
  "step": 4000
24081
  },
 
27082
  {
27083
  "epoch": 2.52,
27084
  "eval_loss": 18.279401779174805,
27085
+ "eval_runtime": 876.9552,
27086
+ "eval_samples_per_second": 3.013,
27087
+ "eval_steps_per_second": 0.377,
27088
  "eval_wer": 1.0005553351844507,
27089
  "step": 4500
27090
  },
 
30091
  {
30092
  "epoch": 2.8,
30093
  "eval_loss": 18.789825439453125,
30094
+ "eval_runtime": 881.3583,
30095
+ "eval_samples_per_second": 2.998,
30096
+ "eval_steps_per_second": 0.376,
30097
  "eval_wer": 1.0,
30098
  "step": 5000
30099
  },
 
32214
  "step": 5352,
32215
  "total_flos": 0.0,
32216
  "train_loss": 5.609615023672491,
32217
+ "train_runtime": 24667.9377,
32218
+ "train_samples_per_second": 3.471,
32219
+ "train_steps_per_second": 0.217
32220
  }
32221
  ],
32222
  "max_steps": 5352,