End of training
Browse files- all_results.json +14 -0
- errs +20 -0
- eval_results.json +9 -0
- logs +10 -0
- train_results.json +8 -0
- trainer_state.json +1429 -0
- wandb/run-20220126_105847-1xdiy2kf/files/config.yaml +20 -0
- wandb/run-20220126_105847-1xdiy2kf/files/output.log +46 -0
- wandb/run-20220126_105847-1xdiy2kf/files/wandb-summary.json +0 -0
- wandb/run-20220126_105847-1xdiy2kf/logs/debug-internal.log +77 -0
- wandb/run-20220126_105847-1xdiy2kf/run-1xdiy2kf.wandb +2 -2
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 500.0,
|
3 |
+
"eval_loss": 0.6521313190460205,
|
4 |
+
"eval_runtime": 134.0142,
|
5 |
+
"eval_samples": 2609,
|
6 |
+
"eval_samples_per_second": 19.468,
|
7 |
+
"eval_steps_per_second": 0.246,
|
8 |
+
"eval_wer": 0.40601336302895324,
|
9 |
+
"train_loss": 0.11533763631184896,
|
10 |
+
"train_runtime": 176050.2174,
|
11 |
+
"train_samples": 5705,
|
12 |
+
"train_samples_per_second": 16.203,
|
13 |
+
"train_steps_per_second": 0.102
|
14 |
+
}
|
errs
CHANGED
@@ -2065,3 +2065,23 @@ Configuration saved in ./checkpoint-18000/config.json
|
|
2065 |
Model weights saved in ./checkpoint-18000/pytorch_model.bin
|
2066 |
Configuration saved in ./checkpoint-18000/preprocessor_config.json
|
2067 |
Configuration saved in ./preprocessor_config.json
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2068 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2069 |
0% 0/33 [00:00<?, ?it/s]
|
2070 |
6% 2/33 [00:04<01:09, 2.23s/it]
|
2071 |
9% 3/33 [00:08<01:34, 3.14s/it]
|
2072 |
12% 4/33 [00:12<01:40, 3.47s/it]
|
2073 |
15% 5/33 [00:17<01:43, 3.69s/it]
|
2074 |
18% 6/33 [00:21<01:44, 3.85s/it]
|
2075 |
21% 7/33 [00:24<01:39, 3.84s/it]
|
2076 |
24% 8/33 [00:28<01:36, 3.87s/it]
|
2077 |
27% 9/33 [00:32<01:33, 3.89s/it]
|
2078 |
30% 10/33 [00:37<01:33, 4.09s/it]
|
2079 |
33% 11/33 [00:41<01:29, 4.06s/it]
|
2080 |
36% 12/33 [00:45<01:24, 4.03s/it]
|
2081 |
39% 13/33 [00:49<01:19, 3.97s/it]
|
2082 |
42% 14/33 [00:53<01:16, 4.02s/it]
|
2083 |
45% 15/33 [00:57<01:13, 4.06s/it]
|
2084 |
48% 16/33 [01:02<01:11, 4.20s/it]
|
2085 |
52% 17/33 [01:06<01:09, 4.34s/it]
|
2086 |
55% 18/33 [01:10<01:03, 4.26s/it]
|
2087 |
58% 19/33 [01:15<00:59, 4.27s/it]
|
2088 |
61% 20/33 [01:19<00:56, 4.34s/it]
|
2089 |
64% 21/33 [01:24<00:52, 4.39s/it]
|
2090 |
67% 22/33 [01:28<00:48, 4.38s/it]
|
2091 |
70% 23/33 [01:32<00:44, 4.41s/it]
|
2092 |
73% 24/33 [01:37<00:39, 4.40s/it]
|
2093 |
76% 25/33 [01:41<00:35, 4.44s/it]
|
2094 |
79% 26/33 [01:46<00:30, 4.39s/it]
|
2095 |
82% 27/33 [01:50<00:26, 4.35s/it]
|
2096 |
85% 28/33 [01:54<00:21, 4.38s/it]
|
2097 |
88% 29/33 [01:58<00:16, 4.13s/it]
|
2098 |
91% 30/33 [02:01<00:11, 3.73s/it]
|
2099 |
94% 31/33 [02:03<00:06, 3.44s/it]
|
2100 |
97% 32/33 [02:06<00:03, 3.19s/it]
|
|
|
|
|
|
|
|
|
|
2065 |
Model weights saved in ./checkpoint-18000/pytorch_model.bin
|
2066 |
Configuration saved in ./checkpoint-18000/preprocessor_config.json
|
2067 |
Configuration saved in ./preprocessor_config.json
|
2068 |
+
Deleting older checkpoint [checkpoint-17500] due to args.save_total_limit
|
2069 |
+
|
2070 |
+
|
2071 |
+
Training completed. Do not forget to share your model on huggingface.co/models =)
|
2072 |
+
|
2073 |
+
|
2074 |
+
|
2075 |
|
2076 |
+
Saving model checkpoint to ./
|
2077 |
+
Configuration saved in ./config.json
|
2078 |
+
Model weights saved in ./pytorch_model.bin
|
2079 |
+
Configuration saved in ./preprocessor_config.json
|
2080 |
+
The following columns in the evaluation set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.
|
2081 |
+
***** Running Evaluation *****
|
2082 |
+
Num examples = 2609
|
2083 |
+
Batch size = 80
|
2084 |
+
|
2085 |
0% 0/33 [00:00<?, ?it/s]
|
2086 |
6% 2/33 [00:04<01:09, 2.23s/it]
|
2087 |
9% 3/33 [00:08<01:34, 3.14s/it]
|
2088 |
12% 4/33 [00:12<01:40, 3.47s/it]
|
2089 |
15% 5/33 [00:17<01:43, 3.69s/it]
|
2090 |
18% 6/33 [00:21<01:44, 3.85s/it]
|
2091 |
21% 7/33 [00:24<01:39, 3.84s/it]
|
2092 |
24% 8/33 [00:28<01:36, 3.87s/it]
|
2093 |
27% 9/33 [00:32<01:33, 3.89s/it]
|
2094 |
30% 10/33 [00:37<01:33, 4.09s/it]
|
2095 |
33% 11/33 [00:41<01:29, 4.06s/it]
|
2096 |
36% 12/33 [00:45<01:24, 4.03s/it]
|
2097 |
39% 13/33 [00:49<01:19, 3.97s/it]
|
2098 |
42% 14/33 [00:53<01:16, 4.02s/it]
|
2099 |
45% 15/33 [00:57<01:13, 4.06s/it]
|
2100 |
48% 16/33 [01:02<01:11, 4.20s/it]
|
2101 |
52% 17/33 [01:06<01:09, 4.34s/it]
|
2102 |
55% 18/33 [01:10<01:03, 4.26s/it]
|
2103 |
58% 19/33 [01:15<00:59, 4.27s/it]
|
2104 |
61% 20/33 [01:19<00:56, 4.34s/it]
|
2105 |
64% 21/33 [01:24<00:52, 4.39s/it]
|
2106 |
67% 22/33 [01:28<00:48, 4.38s/it]
|
2107 |
70% 23/33 [01:32<00:44, 4.41s/it]
|
2108 |
73% 24/33 [01:37<00:39, 4.40s/it]
|
2109 |
76% 25/33 [01:41<00:35, 4.44s/it]
|
2110 |
79% 26/33 [01:46<00:30, 4.39s/it]
|
2111 |
82% 27/33 [01:50<00:26, 4.35s/it]
|
2112 |
85% 28/33 [01:54<00:21, 4.38s/it]
|
2113 |
88% 29/33 [01:58<00:16, 4.13s/it]
|
2114 |
91% 30/33 [02:01<00:11, 3.73s/it]
|
2115 |
94% 31/33 [02:03<00:06, 3.44s/it]
|
2116 |
97% 32/33 [02:06<00:03, 3.19s/it]
|
2117 |
+
Saving model checkpoint to ./
|
2118 |
+
Configuration saved in ./config.json
|
2119 |
+
Model weights saved in ./pytorch_model.bin
|
2120 |
+
Configuration saved in ./preprocessor_config.json
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 500.0,
|
3 |
+
"eval_loss": 0.6521313190460205,
|
4 |
+
"eval_runtime": 134.0142,
|
5 |
+
"eval_samples": 2609,
|
6 |
+
"eval_samples_per_second": 19.468,
|
7 |
+
"eval_steps_per_second": 0.246,
|
8 |
+
"eval_wer": 0.40601336302895324
|
9 |
+
}
|
logs
CHANGED
@@ -308,3 +308,13 @@ xpu_backend=None,
|
|
308 |
{'loss': 0.0113, 'learning_rate': 3.352551457218578e-07, 'epoch': 494.44}
|
309 |
{'loss': 0.011, 'learning_rate': 8.714003300058781e-08, 'epoch': 497.22}
|
310 |
{'loss': 0.0113, 'learning_rate': 1.2890911316176812e-10, 'epoch': 500.0}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
308 |
{'loss': 0.0113, 'learning_rate': 3.352551457218578e-07, 'epoch': 494.44}
|
309 |
{'loss': 0.011, 'learning_rate': 8.714003300058781e-08, 'epoch': 497.22}
|
310 |
{'loss': 0.0113, 'learning_rate': 1.2890911316176812e-10, 'epoch': 500.0}
|
311 |
+
{'eval_loss': 0.6521313190460205, 'eval_wer': 0.40601336302895324, 'eval_runtime': 132.4384, 'eval_samples_per_second': 19.7, 'eval_steps_per_second': 0.249, 'epoch': 500.0}
|
312 |
+
{'train_runtime': 176050.2174, 'train_samples_per_second': 16.203, 'train_steps_per_second': 0.102, 'train_loss': 0.11533763631184896, 'epoch': 500.0}
|
313 |
+
***** train metrics *****
|
314 |
+
epoch = 500.0
|
315 |
+
train_loss = 0.1153
|
316 |
+
train_runtime = 2 days, 0:54:10.21
|
317 |
+
train_samples = 5705
|
318 |
+
train_samples_per_second = 16.203
|
319 |
+
train_steps_per_second = 0.102
|
320 |
+
01/28/2022 11:53:03 - INFO - __main__ - *** Evaluate ***
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 500.0,
|
3 |
+
"train_loss": 0.11533763631184896,
|
4 |
+
"train_runtime": 176050.2174,
|
5 |
+
"train_samples": 5705,
|
6 |
+
"train_samples_per_second": 16.203,
|
7 |
+
"train_steps_per_second": 0.102
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1429 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 500.0,
|
5 |
+
"global_step": 18000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 2.78,
|
12 |
+
"learning_rate": 0.00019800000000000002,
|
13 |
+
"loss": 4.5903,
|
14 |
+
"step": 100
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 5.56,
|
18 |
+
"learning_rate": 0.000398,
|
19 |
+
"loss": 2.9083,
|
20 |
+
"step": 200
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 8.33,
|
24 |
+
"learning_rate": 0.000598,
|
25 |
+
"loss": 1.2823,
|
26 |
+
"step": 300
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 11.11,
|
30 |
+
"learning_rate": 0.0007980000000000001,
|
31 |
+
"loss": 0.3962,
|
32 |
+
"step": 400
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 13.89,
|
36 |
+
"learning_rate": 0.000998,
|
37 |
+
"loss": 0.3034,
|
38 |
+
"step": 500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 13.89,
|
42 |
+
"eval_loss": 0.38567885756492615,
|
43 |
+
"eval_runtime": 133.1769,
|
44 |
+
"eval_samples_per_second": 19.59,
|
45 |
+
"eval_steps_per_second": 0.248,
|
46 |
+
"eval_wer": 0.4354438434616608,
|
47 |
+
"step": 500
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 16.67,
|
51 |
+
"learning_rate": 0.0009999210371864342,
|
52 |
+
"loss": 0.2639,
|
53 |
+
"step": 600
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 19.44,
|
57 |
+
"learning_rate": 0.0009996809758056298,
|
58 |
+
"loss": 0.2354,
|
59 |
+
"step": 700
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 22.22,
|
63 |
+
"learning_rate": 0.000999279885163942,
|
64 |
+
"loss": 0.2158,
|
65 |
+
"step": 800
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 25.0,
|
69 |
+
"learning_rate": 0.000998717894518502,
|
70 |
+
"loss": 0.2063,
|
71 |
+
"step": 900
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 27.78,
|
75 |
+
"learning_rate": 0.000997995184978743,
|
76 |
+
"loss": 0.1926,
|
77 |
+
"step": 1000
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 27.78,
|
81 |
+
"eval_loss": 0.4142022132873535,
|
82 |
+
"eval_runtime": 135.7258,
|
83 |
+
"eval_samples_per_second": 19.223,
|
84 |
+
"eval_steps_per_second": 0.243,
|
85 |
+
"eval_wer": 0.4174355711104041,
|
86 |
+
"step": 1000
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 30.56,
|
90 |
+
"learning_rate": 0.0009971119894480345,
|
91 |
+
"loss": 0.1771,
|
92 |
+
"step": 1100
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 33.33,
|
96 |
+
"learning_rate": 0.0009960685925486266,
|
97 |
+
"loss": 0.1709,
|
98 |
+
"step": 1200
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 36.11,
|
102 |
+
"learning_rate": 0.0009948653305299256,
|
103 |
+
"loss": 0.1724,
|
104 |
+
"step": 1300
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 38.89,
|
108 |
+
"learning_rate": 0.0009935025911601335,
|
109 |
+
"loss": 0.1632,
|
110 |
+
"step": 1400
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 41.67,
|
114 |
+
"learning_rate": 0.0009919808136012837,
|
115 |
+
"loss": 0.1609,
|
116 |
+
"step": 1500
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 41.67,
|
120 |
+
"eval_loss": 0.4701250195503235,
|
121 |
+
"eval_runtime": 133.1213,
|
122 |
+
"eval_samples_per_second": 19.599,
|
123 |
+
"eval_steps_per_second": 0.248,
|
124 |
+
"eval_wer": 0.42958956411072224,
|
125 |
+
"step": 1500
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 44.44,
|
129 |
+
"learning_rate": 0.0009903004882677155,
|
130 |
+
"loss": 0.1521,
|
131 |
+
"step": 1600
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 47.22,
|
135 |
+
"learning_rate": 0.0009884621566680308,
|
136 |
+
"loss": 0.1531,
|
137 |
+
"step": 1700
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 50.0,
|
141 |
+
"learning_rate": 0.0009864664112305846,
|
142 |
+
"loss": 0.1514,
|
143 |
+
"step": 1800
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 52.78,
|
147 |
+
"learning_rate": 0.0009843138951125682,
|
148 |
+
"loss": 0.1468,
|
149 |
+
"step": 1900
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 55.56,
|
153 |
+
"learning_rate": 0.000982005301992741,
|
154 |
+
"loss": 0.1501,
|
155 |
+
"step": 2000
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 55.56,
|
159 |
+
"eval_loss": 0.45478546619415283,
|
160 |
+
"eval_runtime": 133.376,
|
161 |
+
"eval_samples_per_second": 19.561,
|
162 |
+
"eval_steps_per_second": 0.247,
|
163 |
+
"eval_wer": 0.43805281578110083,
|
164 |
+
"step": 2000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 58.33,
|
168 |
+
"learning_rate": 0.0009795413758478834,
|
169 |
+
"loss": 0.1427,
|
170 |
+
"step": 2100
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 61.11,
|
174 |
+
"learning_rate": 0.0009769229107130409,
|
175 |
+
"loss": 0.1441,
|
176 |
+
"step": 2200
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 63.89,
|
180 |
+
"learning_rate": 0.0009741507504256327,
|
181 |
+
"loss": 0.1399,
|
182 |
+
"step": 2300
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 66.67,
|
186 |
+
"learning_rate": 0.0009712257883535152,
|
187 |
+
"loss": 0.1379,
|
188 |
+
"step": 2400
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 69.44,
|
192 |
+
"learning_rate": 0.0009681489671070803,
|
193 |
+
"loss": 0.1382,
|
194 |
+
"step": 2500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 69.44,
|
198 |
+
"eval_loss": 0.523300290107727,
|
199 |
+
"eval_runtime": 131.9566,
|
200 |
+
"eval_samples_per_second": 19.772,
|
201 |
+
"eval_steps_per_second": 0.25,
|
202 |
+
"eval_wer": 0.4544066178810054,
|
203 |
+
"step": 2500
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 72.22,
|
207 |
+
"learning_rate": 0.0009649212782354872,
|
208 |
+
"loss": 0.1372,
|
209 |
+
"step": 2600
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 75.0,
|
213 |
+
"learning_rate": 0.0009615437619071199,
|
214 |
+
"loss": 0.1345,
|
215 |
+
"step": 2700
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 77.78,
|
219 |
+
"learning_rate": 0.0009580175065743799,
|
220 |
+
"loss": 0.1346,
|
221 |
+
"step": 2800
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 80.56,
|
225 |
+
"learning_rate": 0.0009543436486229162,
|
226 |
+
"loss": 0.1367,
|
227 |
+
"step": 2900
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 83.33,
|
231 |
+
"learning_rate": 0.0009505233720054086,
|
232 |
+
"loss": 0.1287,
|
233 |
+
"step": 3000
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 83.33,
|
237 |
+
"eval_loss": 0.48360341787338257,
|
238 |
+
"eval_runtime": 132.2498,
|
239 |
+
"eval_samples_per_second": 19.728,
|
240 |
+
"eval_steps_per_second": 0.25,
|
241 |
+
"eval_wer": 0.43658924594336623,
|
242 |
+
"step": 3000
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 86.11,
|
246 |
+
"learning_rate": 0.0009465579078600233,
|
247 |
+
"loss": 0.1226,
|
248 |
+
"step": 3100
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 88.89,
|
252 |
+
"learning_rate": 0.0009424485341136599,
|
253 |
+
"loss": 0.1258,
|
254 |
+
"step": 3200
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 91.67,
|
258 |
+
"learning_rate": 0.0009381965750701229,
|
259 |
+
"loss": 0.1222,
|
260 |
+
"step": 3300
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 94.44,
|
264 |
+
"learning_rate": 0.0009338034009833446,
|
265 |
+
"loss": 0.1182,
|
266 |
+
"step": 3400
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 97.22,
|
270 |
+
"learning_rate": 0.0009292704276158022,
|
271 |
+
"loss": 0.1164,
|
272 |
+
"step": 3500
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 97.22,
|
276 |
+
"eval_loss": 0.5202445983886719,
|
277 |
+
"eval_runtime": 132.7793,
|
278 |
+
"eval_samples_per_second": 19.649,
|
279 |
+
"eval_steps_per_second": 0.249,
|
280 |
+
"eval_wer": 0.43948456888323256,
|
281 |
+
"step": 3500
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 100.0,
|
285 |
+
"learning_rate": 0.0009245991157822682,
|
286 |
+
"loss": 0.1212,
|
287 |
+
"step": 3600
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 102.78,
|
291 |
+
"learning_rate": 0.000919790970879042,
|
292 |
+
"loss": 0.1139,
|
293 |
+
"step": 3700
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 105.56,
|
297 |
+
"learning_rate": 0.000914847542398815,
|
298 |
+
"loss": 0.115,
|
299 |
+
"step": 3800
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 108.33,
|
303 |
+
"learning_rate": 0.0009097704234313245,
|
304 |
+
"loss": 0.1123,
|
305 |
+
"step": 3900
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 111.11,
|
309 |
+
"learning_rate": 0.0009045612501499573,
|
310 |
+
"loss": 0.1101,
|
311 |
+
"step": 4000
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 111.11,
|
315 |
+
"eval_loss": 0.5120447874069214,
|
316 |
+
"eval_runtime": 131.3001,
|
317 |
+
"eval_samples_per_second": 19.871,
|
318 |
+
"eval_steps_per_second": 0.251,
|
319 |
+
"eval_wer": 0.43827553293032134,
|
320 |
+
"step": 4000
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 113.89,
|
324 |
+
"learning_rate": 0.0008992217012844713,
|
325 |
+
"loss": 0.1092,
|
326 |
+
"step": 4100
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 116.67,
|
330 |
+
"learning_rate": 0.0008937534975799996,
|
331 |
+
"loss": 0.1104,
|
332 |
+
"step": 4200
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 119.44,
|
336 |
+
"learning_rate": 0.0008881584012425165,
|
337 |
+
"loss": 0.1021,
|
338 |
+
"step": 4300
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 122.22,
|
342 |
+
"learning_rate": 0.0008824382153709421,
|
343 |
+
"loss": 0.1063,
|
344 |
+
"step": 4400
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 125.0,
|
348 |
+
"learning_rate": 0.0008765947833760678,
|
349 |
+
"loss": 0.1107,
|
350 |
+
"step": 4500
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 125.0,
|
354 |
+
"eval_loss": 0.5130612850189209,
|
355 |
+
"eval_runtime": 133.0961,
|
356 |
+
"eval_samples_per_second": 19.602,
|
357 |
+
"eval_steps_per_second": 0.248,
|
358 |
+
"eval_wer": 0.4446706967865097,
|
359 |
+
"step": 4500
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 127.78,
|
363 |
+
"learning_rate": 0.000870629988386491,
|
364 |
+
"loss": 0.1054,
|
365 |
+
"step": 4600
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 130.56,
|
369 |
+
"learning_rate": 0.0008645457526417502,
|
370 |
+
"loss": 0.1037,
|
371 |
+
"step": 4700
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 133.33,
|
375 |
+
"learning_rate": 0.0008583440368728572,
|
376 |
+
"loss": 0.1,
|
377 |
+
"step": 4800
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 136.11,
|
381 |
+
"learning_rate": 0.0008520268396704223,
|
382 |
+
"loss": 0.0967,
|
383 |
+
"step": 4900
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 138.89,
|
387 |
+
"learning_rate": 0.0008455961968405809,
|
388 |
+
"loss": 0.0942,
|
389 |
+
"step": 5000
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 138.89,
|
393 |
+
"eval_loss": 0.5256752967834473,
|
394 |
+
"eval_runtime": 133.1352,
|
395 |
+
"eval_samples_per_second": 19.597,
|
396 |
+
"eval_steps_per_second": 0.248,
|
397 |
+
"eval_wer": 0.43748011454024816,
|
398 |
+
"step": 5000
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 141.67,
|
402 |
+
"learning_rate": 0.0008390541807489265,
|
403 |
+
"loss": 0.0987,
|
404 |
+
"step": 5100
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 144.44,
|
408 |
+
"learning_rate": 0.0008324028996526611,
|
409 |
+
"loss": 0.094,
|
410 |
+
"step": 5200
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 147.22,
|
414 |
+
"learning_rate": 0.0008256444970211793,
|
415 |
+
"loss": 0.0935,
|
416 |
+
"step": 5300
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 150.0,
|
420 |
+
"learning_rate": 0.000818781150845306,
|
421 |
+
"loss": 0.0906,
|
422 |
+
"step": 5400
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 152.78,
|
426 |
+
"learning_rate": 0.0008118150729354068,
|
427 |
+
"loss": 0.0909,
|
428 |
+
"step": 5500
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 152.78,
|
432 |
+
"eval_loss": 0.5312919020652771,
|
433 |
+
"eval_runtime": 133.5185,
|
434 |
+
"eval_samples_per_second": 19.54,
|
435 |
+
"eval_steps_per_second": 0.247,
|
436 |
+
"eval_wer": 0.47133312122176263,
|
437 |
+
"step": 5500
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 155.56,
|
441 |
+
"learning_rate": 0.0008047485082086017,
|
442 |
+
"loss": 0.0881,
|
443 |
+
"step": 5600
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 158.33,
|
447 |
+
"learning_rate": 0.0007975837339653084,
|
448 |
+
"loss": 0.0921,
|
449 |
+
"step": 5700
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 161.11,
|
453 |
+
"learning_rate": 0.0007903230591553503,
|
454 |
+
"loss": 0.0838,
|
455 |
+
"step": 5800
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 163.89,
|
459 |
+
"learning_rate": 0.0007829688236338643,
|
460 |
+
"loss": 0.0775,
|
461 |
+
"step": 5900
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 166.67,
|
465 |
+
"learning_rate": 0.0007755233974072504,
|
466 |
+
"loss": 0.0807,
|
467 |
+
"step": 6000
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 166.67,
|
471 |
+
"eval_loss": 0.5847254991531372,
|
472 |
+
"eval_runtime": 133.1812,
|
473 |
+
"eval_samples_per_second": 19.59,
|
474 |
+
"eval_steps_per_second": 0.248,
|
475 |
+
"eval_wer": 0.44708876869233216,
|
476 |
+
"step": 6000
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 169.44,
|
480 |
+
"learning_rate": 0.0007679891798694021,
|
481 |
+
"loss": 0.0801,
|
482 |
+
"step": 6100
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 172.22,
|
486 |
+
"learning_rate": 0.000760368599028469,
|
487 |
+
"loss": 0.0952,
|
488 |
+
"step": 6200
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 175.0,
|
492 |
+
"learning_rate": 0.0007526641107243966,
|
493 |
+
"loss": 0.0813,
|
494 |
+
"step": 6300
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 177.78,
|
498 |
+
"learning_rate": 0.0007448781978374969,
|
499 |
+
"loss": 0.0795,
|
500 |
+
"step": 6400
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 180.56,
|
504 |
+
"learning_rate": 0.0007370133694883051,
|
505 |
+
"loss": 0.0767,
|
506 |
+
"step": 6500
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 180.56,
|
510 |
+
"eval_loss": 0.5318175554275513,
|
511 |
+
"eval_runtime": 135.804,
|
512 |
+
"eval_samples_per_second": 19.212,
|
513 |
+
"eval_steps_per_second": 0.243,
|
514 |
+
"eval_wer": 0.4534521158129176,
|
515 |
+
"step": 6500
|
516 |
+
},
|
517 |
+
{
|
518 |
+
"epoch": 183.33,
|
519 |
+
"learning_rate": 0.0007290721602289801,
|
520 |
+
"loss": 0.0762,
|
521 |
+
"step": 6600
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 186.11,
|
525 |
+
"learning_rate": 0.0007210571292265096,
|
526 |
+
"loss": 0.0729,
|
527 |
+
"step": 6700
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 188.89,
|
531 |
+
"learning_rate": 0.0007129708594379816,
|
532 |
+
"loss": 0.0751,
|
533 |
+
"step": 6800
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 191.67,
|
537 |
+
"learning_rate": 0.0007048159567781905,
|
538 |
+
"loss": 0.0743,
|
539 |
+
"step": 6900
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 194.44,
|
543 |
+
"learning_rate": 0.0006965950492798443,
|
544 |
+
"loss": 0.0729,
|
545 |
+
"step": 7000
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 194.44,
|
549 |
+
"eval_loss": 0.5796982645988464,
|
550 |
+
"eval_runtime": 132.2018,
|
551 |
+
"eval_samples_per_second": 19.735,
|
552 |
+
"eval_steps_per_second": 0.25,
|
553 |
+
"eval_wer": 0.4584155265669742,
|
554 |
+
"step": 7000
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 197.22,
|
558 |
+
"learning_rate": 0.0006883107862466433,
|
559 |
+
"loss": 0.0791,
|
560 |
+
"step": 7100
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 200.0,
|
564 |
+
"learning_rate": 0.0006799658373995054,
|
565 |
+
"loss": 0.0737,
|
566 |
+
"step": 7200
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 202.78,
|
570 |
+
"learning_rate": 0.0006715628920162093,
|
571 |
+
"loss": 0.0694,
|
572 |
+
"step": 7300
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 205.56,
|
576 |
+
"learning_rate": 0.0006631046580647384,
|
577 |
+
"loss": 0.0687,
|
578 |
+
"step": 7400
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 208.33,
|
582 |
+
"learning_rate": 0.0006545938613305993,
|
583 |
+
"loss": 0.072,
|
584 |
+
"step": 7500
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 208.33,
|
588 |
+
"eval_loss": 0.5266388654708862,
|
589 |
+
"eval_runtime": 130.3709,
|
590 |
+
"eval_samples_per_second": 20.012,
|
591 |
+
"eval_steps_per_second": 0.253,
|
592 |
+
"eval_wer": 0.44339802736239264,
|
593 |
+
"step": 7500
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 211.11,
|
597 |
+
"learning_rate": 0.000646033244538398,
|
598 |
+
"loss": 0.0647,
|
599 |
+
"step": 7600
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 213.89,
|
603 |
+
"learning_rate": 0.000637425566467959,
|
604 |
+
"loss": 0.0631,
|
605 |
+
"step": 7700
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 216.67,
|
609 |
+
"learning_rate": 0.0006287736010652693,
|
610 |
+
"loss": 0.0606,
|
611 |
+
"step": 7800
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 219.44,
|
615 |
+
"learning_rate": 0.000620080136548535,
|
616 |
+
"loss": 0.0645,
|
617 |
+
"step": 7900
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"epoch": 222.22,
|
621 |
+
"learning_rate": 0.0006113479745096386,
|
622 |
+
"loss": 0.0593,
|
623 |
+
"step": 8000
|
624 |
+
},
|
625 |
+
{
|
626 |
+
"epoch": 222.22,
|
627 |
+
"eval_loss": 0.579177737236023,
|
628 |
+
"eval_runtime": 133.0716,
|
629 |
+
"eval_samples_per_second": 19.606,
|
630 |
+
"eval_steps_per_second": 0.248,
|
631 |
+
"eval_wer": 0.43888005090677695,
|
632 |
+
"step": 8000
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 225.0,
|
636 |
+
"learning_rate": 0.0006025799290112865,
|
637 |
+
"loss": 0.0596,
|
638 |
+
"step": 8100
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 227.78,
|
642 |
+
"learning_rate": 0.0005937788256801371,
|
643 |
+
"loss": 0.0606,
|
644 |
+
"step": 8200
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 230.56,
|
648 |
+
"learning_rate": 0.0005849475007962031,
|
649 |
+
"loss": 0.0591,
|
650 |
+
"step": 8300
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 233.33,
|
654 |
+
"learning_rate": 0.0005760888003788196,
|
655 |
+
"loss": 0.0544,
|
656 |
+
"step": 8400
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 236.11,
|
660 |
+
"learning_rate": 0.0005672055792694753,
|
661 |
+
"loss": 0.0524,
|
662 |
+
"step": 8500
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 236.11,
|
666 |
+
"eval_loss": 0.5740395784378052,
|
667 |
+
"eval_runtime": 132.5642,
|
668 |
+
"eval_samples_per_second": 19.681,
|
669 |
+
"eval_steps_per_second": 0.249,
|
670 |
+
"eval_wer": 0.43732103086223356,
|
671 |
+
"step": 8500
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"epoch": 238.89,
|
675 |
+
"learning_rate": 0.0005583007002117978,
|
676 |
+
"loss": 0.0504,
|
677 |
+
"step": 8600
|
678 |
+
},
|
679 |
+
{
|
680 |
+
"epoch": 241.67,
|
681 |
+
"learning_rate": 0.0005493770329289953,
|
682 |
+
"loss": 0.0494,
|
683 |
+
"step": 8700
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 244.44,
|
687 |
+
"learning_rate": 0.0005404374531990474,
|
688 |
+
"loss": 0.0484,
|
689 |
+
"step": 8800
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 247.22,
|
693 |
+
"learning_rate": 0.0005314848419279442,
|
694 |
+
"loss": 0.0489,
|
695 |
+
"step": 8900
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 250.0,
|
699 |
+
"learning_rate": 0.0005225220842212748,
|
700 |
+
"loss": 0.0494,
|
701 |
+
"step": 9000
|
702 |
+
},
|
703 |
+
{
|
704 |
+
"epoch": 250.0,
|
705 |
+
"eval_loss": 0.5520852208137512,
|
706 |
+
"eval_runtime": 133.6258,
|
707 |
+
"eval_samples_per_second": 19.525,
|
708 |
+
"eval_steps_per_second": 0.247,
|
709 |
+
"eval_wer": 0.44358892777601017,
|
710 |
+
"step": 9000
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 252.78,
|
714 |
+
"learning_rate": 0.0005135520684544602,
|
715 |
+
"loss": 0.0499,
|
716 |
+
"step": 9100
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 255.56,
|
720 |
+
"learning_rate": 0.0005045776853419344,
|
721 |
+
"loss": 0.0487,
|
722 |
+
"step": 9200
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 258.33,
|
726 |
+
"learning_rate": 0.0004956018270055703,
|
727 |
+
"loss": 0.0523,
|
728 |
+
"step": 9300
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 261.11,
|
732 |
+
"learning_rate": 0.00048662738604265206,
|
733 |
+
"loss": 0.0479,
|
734 |
+
"step": 9400
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 263.89,
|
738 |
+
"learning_rate": 0.0004776572545936954,
|
739 |
+
"loss": 0.0469,
|
740 |
+
"step": 9500
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 263.89,
|
744 |
+
"eval_loss": 0.5630596876144409,
|
745 |
+
"eval_runtime": 130.7272,
|
746 |
+
"eval_samples_per_second": 19.958,
|
747 |
+
"eval_steps_per_second": 0.252,
|
748 |
+
"eval_wer": 0.4345847916003818,
|
749 |
+
"step": 9500
|
750 |
+
},
|
751 |
+
{
|
752 |
+
"epoch": 266.67,
|
753 |
+
"learning_rate": 0.0004686943234104146,
|
754 |
+
"loss": 0.0467,
|
755 |
+
"step": 9600
|
756 |
+
},
|
757 |
+
{
|
758 |
+
"epoch": 269.44,
|
759 |
+
"learning_rate": 0.00045974148092413597,
|
760 |
+
"loss": 0.0438,
|
761 |
+
"step": 9700
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 272.22,
|
765 |
+
"learning_rate": 0.00045080161231496064,
|
766 |
+
"loss": 0.0422,
|
767 |
+
"step": 9800
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 275.0,
|
771 |
+
"learning_rate": 0.00044187759858197486,
|
772 |
+
"loss": 0.042,
|
773 |
+
"step": 9900
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 277.78,
|
777 |
+
"learning_rate": 0.0004329723156148063,
|
778 |
+
"loss": 0.0417,
|
779 |
+
"step": 10000
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 277.78,
|
783 |
+
"eval_loss": 0.5777372121810913,
|
784 |
+
"eval_runtime": 130.7332,
|
785 |
+
"eval_samples_per_second": 19.957,
|
786 |
+
"eval_steps_per_second": 0.252,
|
787 |
+
"eval_wer": 0.43057588291441296,
|
788 |
+
"step": 10000
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 280.56,
|
792 |
+
"learning_rate": 0.0004240886332668285,
|
793 |
+
"loss": 0.0406,
|
794 |
+
"step": 10100
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 283.33,
|
798 |
+
"learning_rate": 0.00041522941443031025,
|
799 |
+
"loss": 0.0385,
|
800 |
+
"step": 10200
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 286.11,
|
804 |
+
"learning_rate": 0.0004063975141138074,
|
805 |
+
"loss": 0.0384,
|
806 |
+
"step": 10300
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 288.89,
|
810 |
+
"learning_rate": 0.00039759577852209704,
|
811 |
+
"loss": 0.0369,
|
812 |
+
"step": 10400
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 291.67,
|
816 |
+
"learning_rate": 0.0003888270441389465,
|
817 |
+
"loss": 0.0379,
|
818 |
+
"step": 10500
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 291.67,
|
822 |
+
"eval_loss": 0.5934527516365051,
|
823 |
+
"eval_runtime": 131.6738,
|
824 |
+
"eval_samples_per_second": 19.814,
|
825 |
+
"eval_steps_per_second": 0.251,
|
826 |
+
"eval_wer": 0.42828507795100224,
|
827 |
+
"step": 10500
|
828 |
+
},
|
829 |
+
{
|
830 |
+
"epoch": 294.44,
|
831 |
+
"learning_rate": 0.0003800941368130171,
|
832 |
+
"loss": 0.0399,
|
833 |
+
"step": 10600
|
834 |
+
},
|
835 |
+
{
|
836 |
+
"epoch": 297.22,
|
837 |
+
"learning_rate": 0.0003713998708471946,
|
838 |
+
"loss": 0.0359,
|
839 |
+
"step": 10700
|
840 |
+
},
|
841 |
+
{
|
842 |
+
"epoch": 300.0,
|
843 |
+
"learning_rate": 0.0003627470480916394,
|
844 |
+
"loss": 0.0345,
|
845 |
+
"step": 10800
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 302.78,
|
849 |
+
"learning_rate": 0.00035413845704085215,
|
850 |
+
"loss": 0.0346,
|
851 |
+
"step": 10900
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 305.56,
|
855 |
+
"learning_rate": 0.00034557687193504045,
|
856 |
+
"loss": 0.0319,
|
857 |
+
"step": 11000
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 305.56,
|
861 |
+
"eval_loss": 0.5892442464828491,
|
862 |
+
"eval_runtime": 130.692,
|
863 |
+
"eval_samples_per_second": 19.963,
|
864 |
+
"eval_steps_per_second": 0.253,
|
865 |
+
"eval_wer": 0.41880369074132995,
|
866 |
+
"step": 11000
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 308.33,
|
870 |
+
"learning_rate": 0.00033706505186608136,
|
871 |
+
"loss": 0.0318,
|
872 |
+
"step": 11100
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 311.11,
|
876 |
+
"learning_rate": 0.00032860573988836573,
|
877 |
+
"loss": 0.0301,
|
878 |
+
"step": 11200
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 313.89,
|
882 |
+
"learning_rate": 0.0003202016621348088,
|
883 |
+
"loss": 0.0322,
|
884 |
+
"step": 11300
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 316.67,
|
888 |
+
"learning_rate": 0.00031185552693831594,
|
889 |
+
"loss": 0.0331,
|
890 |
+
"step": 11400
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 319.44,
|
894 |
+
"learning_rate": 0.0003035700239589846,
|
895 |
+
"loss": 0.0311,
|
896 |
+
"step": 11500
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 319.44,
|
900 |
+
"eval_loss": 0.6010639071464539,
|
901 |
+
"eval_runtime": 132.2371,
|
902 |
+
"eval_samples_per_second": 19.73,
|
903 |
+
"eval_steps_per_second": 0.25,
|
904 |
+
"eval_wer": 0.4210626789691378,
|
905 |
+
"step": 11500
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 322.22,
|
909 |
+
"learning_rate": 0.00029534782331732204,
|
910 |
+
"loss": 0.0291,
|
911 |
+
"step": 11600
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 325.0,
|
915 |
+
"learning_rate": 0.00028719157473376303,
|
916 |
+
"loss": 0.0287,
|
917 |
+
"step": 11700
|
918 |
+
},
|
919 |
+
{
|
920 |
+
"epoch": 327.78,
|
921 |
+
"learning_rate": 0.00027918443530500935,
|
922 |
+
"loss": 0.0279,
|
923 |
+
"step": 11800
|
924 |
+
},
|
925 |
+
{
|
926 |
+
"epoch": 330.56,
|
927 |
+
"learning_rate": 0.0002711672294401907,
|
928 |
+
"loss": 0.0294,
|
929 |
+
"step": 11900
|
930 |
+
},
|
931 |
+
{
|
932 |
+
"epoch": 333.33,
|
933 |
+
"learning_rate": 0.00026322376817181157,
|
934 |
+
"loss": 0.0269,
|
935 |
+
"step": 12000
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 333.33,
|
939 |
+
"eval_loss": 0.5972930192947388,
|
940 |
+
"eval_runtime": 133.0245,
|
941 |
+
"eval_samples_per_second": 19.613,
|
942 |
+
"eval_steps_per_second": 0.248,
|
943 |
+
"eval_wer": 0.4232262169901368,
|
944 |
+
"step": 12000
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 336.11,
|
948 |
+
"learning_rate": 0.0002553566113926006,
|
949 |
+
"loss": 0.0251,
|
950 |
+
"step": 12100
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 338.89,
|
954 |
+
"learning_rate": 0.00024756829440508705,
|
955 |
+
"loss": 0.0261,
|
956 |
+
"step": 12200
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 341.67,
|
960 |
+
"learning_rate": 0.0002398613271045611,
|
961 |
+
"loss": 0.025,
|
962 |
+
"step": 12300
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 344.44,
|
966 |
+
"learning_rate": 0.00023223819317022654,
|
967 |
+
"loss": 0.0264,
|
968 |
+
"step": 12400
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 347.22,
|
972 |
+
"learning_rate": 0.00022470134926479935,
|
973 |
+
"loss": 0.0271,
|
974 |
+
"step": 12500
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 347.22,
|
978 |
+
"eval_loss": 0.6094068288803101,
|
979 |
+
"eval_runtime": 132.9769,
|
980 |
+
"eval_samples_per_second": 19.62,
|
981 |
+
"eval_steps_per_second": 0.248,
|
982 |
+
"eval_wer": 0.4428253261215399,
|
983 |
+
"step": 12500
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 350.0,
|
987 |
+
"learning_rate": 0.00021725322424281286,
|
988 |
+
"loss": 0.0246,
|
989 |
+
"step": 12600
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 352.78,
|
993 |
+
"learning_rate": 0.00020989621836788614,
|
994 |
+
"loss": 0.0245,
|
995 |
+
"step": 12700
|
996 |
+
},
|
997 |
+
{
|
998 |
+
"epoch": 355.56,
|
999 |
+
"learning_rate": 0.00020263270253920428,
|
1000 |
+
"loss": 0.0229,
|
1001 |
+
"step": 12800
|
1002 |
+
},
|
1003 |
+
{
|
1004 |
+
"epoch": 358.33,
|
1005 |
+
"learning_rate": 0.00019546501752746288,
|
1006 |
+
"loss": 0.0229,
|
1007 |
+
"step": 12900
|
1008 |
+
},
|
1009 |
+
{
|
1010 |
+
"epoch": 361.11,
|
1011 |
+
"learning_rate": 0.0001883954732205217,
|
1012 |
+
"loss": 0.0236,
|
1013 |
+
"step": 13000
|
1014 |
+
},
|
1015 |
+
{
|
1016 |
+
"epoch": 361.11,
|
1017 |
+
"eval_loss": 0.611167311668396,
|
1018 |
+
"eval_runtime": 132.3797,
|
1019 |
+
"eval_samples_per_second": 19.708,
|
1020 |
+
"eval_steps_per_second": 0.249,
|
1021 |
+
"eval_wer": 0.42373528475978367,
|
1022 |
+
"step": 13000
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 363.89,
|
1026 |
+
"learning_rate": 0.00018142634787900996,
|
1027 |
+
"loss": 0.0229,
|
1028 |
+
"step": 13100
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 366.67,
|
1032 |
+
"learning_rate": 0.00017455988740212576,
|
1033 |
+
"loss": 0.0221,
|
1034 |
+
"step": 13200
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 369.44,
|
1038 |
+
"learning_rate": 0.0001677983046038624,
|
1039 |
+
"loss": 0.0208,
|
1040 |
+
"step": 13300
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 372.22,
|
1044 |
+
"learning_rate": 0.00016114377849989813,
|
1045 |
+
"loss": 0.0208,
|
1046 |
+
"step": 13400
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 375.0,
|
1050 |
+
"learning_rate": 0.00015459845360537756,
|
1051 |
+
"loss": 0.0202,
|
1052 |
+
"step": 13500
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 375.0,
|
1056 |
+
"eval_loss": 0.605171799659729,
|
1057 |
+
"eval_runtime": 132.1498,
|
1058 |
+
"eval_samples_per_second": 19.743,
|
1059 |
+
"eval_steps_per_second": 0.25,
|
1060 |
+
"eval_wer": 0.4233534839325485,
|
1061 |
+
"step": 13500
|
1062 |
+
},
|
1063 |
+
{
|
1064 |
+
"epoch": 377.78,
|
1065 |
+
"learning_rate": 0.0001481644392438113,
|
1066 |
+
"loss": 0.0197,
|
1067 |
+
"step": 13600
|
1068 |
+
},
|
1069 |
+
{
|
1070 |
+
"epoch": 380.56,
|
1071 |
+
"learning_rate": 0.00014184380886731607,
|
1072 |
+
"loss": 0.0195,
|
1073 |
+
"step": 13700
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 383.33,
|
1077 |
+
"learning_rate": 0.0001356385993884165,
|
1078 |
+
"loss": 0.0186,
|
1079 |
+
"step": 13800
|
1080 |
+
},
|
1081 |
+
{
|
1082 |
+
"epoch": 386.11,
|
1083 |
+
"learning_rate": 0.00012955081052362072,
|
1084 |
+
"loss": 0.0186,
|
1085 |
+
"step": 13900
|
1086 |
+
},
|
1087 |
+
{
|
1088 |
+
"epoch": 388.89,
|
1089 |
+
"learning_rate": 0.00012358240414898276,
|
1090 |
+
"loss": 0.0175,
|
1091 |
+
"step": 14000
|
1092 |
+
},
|
1093 |
+
{
|
1094 |
+
"epoch": 388.89,
|
1095 |
+
"eval_loss": 0.631072998046875,
|
1096 |
+
"eval_runtime": 131.5592,
|
1097 |
+
"eval_samples_per_second": 19.831,
|
1098 |
+
"eval_steps_per_second": 0.251,
|
1099 |
+
"eval_wer": 0.4188673242125358,
|
1100 |
+
"step": 14000
|
1101 |
+
},
|
1102 |
+
{
|
1103 |
+
"epoch": 391.67,
|
1104 |
+
"learning_rate": 0.00011773530366786184,
|
1105 |
+
"loss": 0.0164,
|
1106 |
+
"step": 14100
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"epoch": 394.44,
|
1110 |
+
"learning_rate": 0.0001120113933910767,
|
1111 |
+
"loss": 0.0166,
|
1112 |
+
"step": 14200
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 397.22,
|
1116 |
+
"learning_rate": 0.000106412517929661,
|
1117 |
+
"loss": 0.0163,
|
1118 |
+
"step": 14300
|
1119 |
+
},
|
1120 |
+
{
|
1121 |
+
"epoch": 400.0,
|
1122 |
+
"learning_rate": 0.00010094048160041091,
|
1123 |
+
"loss": 0.0159,
|
1124 |
+
"step": 14400
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 402.78,
|
1128 |
+
"learning_rate": 9.559704784441814e-05,
|
1129 |
+
"loss": 0.0158,
|
1130 |
+
"step": 14500
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 402.78,
|
1134 |
+
"eval_loss": 0.618556797504425,
|
1135 |
+
"eval_runtime": 132.4333,
|
1136 |
+
"eval_samples_per_second": 19.7,
|
1137 |
+
"eval_steps_per_second": 0.249,
|
1138 |
+
"eval_wer": 0.4137130130448616,
|
1139 |
+
"step": 14500
|
1140 |
+
},
|
1141 |
+
{
|
1142 |
+
"epoch": 405.56,
|
1143 |
+
"learning_rate": 9.038393865877726e-05,
|
1144 |
+
"loss": 0.015,
|
1145 |
+
"step": 14600
|
1146 |
+
},
|
1147 |
+
{
|
1148 |
+
"epoch": 408.33,
|
1149 |
+
"learning_rate": 8.530283404164612e-05,
|
1150 |
+
"loss": 0.0156,
|
1151 |
+
"step": 14700
|
1152 |
+
},
|
1153 |
+
{
|
1154 |
+
"epoch": 411.11,
|
1155 |
+
"learning_rate": 8.03553714508441e-05,
|
1156 |
+
"loss": 0.0146,
|
1157 |
+
"step": 14800
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 413.89,
|
1161 |
+
"learning_rate": 7.554314527615763e-05,
|
1162 |
+
"loss": 0.0146,
|
1163 |
+
"step": 14900
|
1164 |
+
},
|
1165 |
+
{
|
1166 |
+
"epoch": 416.67,
|
1167 |
+
"learning_rate": 7.086770632552514e-05,
|
1168 |
+
"loss": 0.0141,
|
1169 |
+
"step": 15000
|
1170 |
+
},
|
1171 |
+
{
|
1172 |
+
"epoch": 416.67,
|
1173 |
+
"eval_loss": 0.6352781057357788,
|
1174 |
+
"eval_runtime": 132.6132,
|
1175 |
+
"eval_samples_per_second": 19.674,
|
1176 |
+
"eval_steps_per_second": 0.249,
|
1177 |
+
"eval_wer": 0.412249443207127,
|
1178 |
+
"step": 15000
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 419.44,
|
1182 |
+
"learning_rate": 6.633056132526849e-05,
|
1183 |
+
"loss": 0.0138,
|
1184 |
+
"step": 15100
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 422.22,
|
1188 |
+
"learning_rate": 6.193317243452734e-05,
|
1189 |
+
"loss": 0.0138,
|
1190 |
+
"step": 15200
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 425.0,
|
1194 |
+
"learning_rate": 5.7676956774059205e-05,
|
1195 |
+
"loss": 0.0131,
|
1196 |
+
"step": 15300
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 427.78,
|
1200 |
+
"learning_rate": 5.356328596955179e-05,
|
1201 |
+
"loss": 0.0131,
|
1202 |
+
"step": 15400
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 430.56,
|
1206 |
+
"learning_rate": 4.963246731369253e-05,
|
1207 |
+
"loss": 0.013,
|
1208 |
+
"step": 15500
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 430.56,
|
1212 |
+
"eval_loss": 0.6343812942504883,
|
1213 |
+
"eval_runtime": 131.5808,
|
1214 |
+
"eval_samples_per_second": 19.828,
|
1215 |
+
"eval_steps_per_second": 0.251,
|
1216 |
+
"eval_wer": 0.40687241489023224,
|
1217 |
+
"step": 15500
|
1218 |
+
},
|
1219 |
+
{
|
1220 |
+
"epoch": 433.33,
|
1221 |
+
"learning_rate": 4.580635924447718e-05,
|
1222 |
+
"loss": 0.0127,
|
1223 |
+
"step": 15600
|
1224 |
+
},
|
1225 |
+
{
|
1226 |
+
"epoch": 436.11,
|
1227 |
+
"learning_rate": 4.212662149914887e-05,
|
1228 |
+
"loss": 0.0126,
|
1229 |
+
"step": 15700
|
1230 |
+
},
|
1231 |
+
{
|
1232 |
+
"epoch": 438.89,
|
1233 |
+
"learning_rate": 3.859443992523443e-05,
|
1234 |
+
"loss": 0.0125,
|
1235 |
+
"step": 15800
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 441.67,
|
1239 |
+
"learning_rate": 3.521095281819786e-05,
|
1240 |
+
"loss": 0.0127,
|
1241 |
+
"step": 15900
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 444.44,
|
1245 |
+
"learning_rate": 3.1977250554608205e-05,
|
1246 |
+
"loss": 0.0117,
|
1247 |
+
"step": 16000
|
1248 |
+
},
|
1249 |
+
{
|
1250 |
+
"epoch": 444.44,
|
1251 |
+
"eval_loss": 0.6442536115646362,
|
1252 |
+
"eval_runtime": 132.782,
|
1253 |
+
"eval_samples_per_second": 19.649,
|
1254 |
+
"eval_steps_per_second": 0.249,
|
1255 |
+
"eval_wer": 0.40801781737193765,
|
1256 |
+
"step": 16000
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 447.22,
|
1260 |
+
"learning_rate": 2.8894375240750613e-05,
|
1261 |
+
"loss": 0.0122,
|
1262 |
+
"step": 16100
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 450.0,
|
1266 |
+
"learning_rate": 2.5963320376792666e-05,
|
1267 |
+
"loss": 0.0127,
|
1268 |
+
"step": 16200
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 452.78,
|
1272 |
+
"learning_rate": 2.318503053661475e-05,
|
1273 |
+
"loss": 0.0125,
|
1274 |
+
"step": 16300
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 455.56,
|
1278 |
+
"learning_rate": 2.056040106340823e-05,
|
1279 |
+
"loss": 0.0121,
|
1280 |
+
"step": 16400
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 458.33,
|
1284 |
+
"learning_rate": 1.809027778113803e-05,
|
1285 |
+
"loss": 0.0122,
|
1286 |
+
"step": 16500
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 458.33,
|
1290 |
+
"eval_loss": 0.6512282490730286,
|
1291 |
+
"eval_runtime": 133.1307,
|
1292 |
+
"eval_samples_per_second": 19.597,
|
1293 |
+
"eval_steps_per_second": 0.248,
|
1294 |
+
"eval_wer": 0.4069360483614381,
|
1295 |
+
"step": 16500
|
1296 |
+
},
|
1297 |
+
{
|
1298 |
+
"epoch": 461.11,
|
1299 |
+
"learning_rate": 1.5775456721964065e-05,
|
1300 |
+
"loss": 0.0113,
|
1301 |
+
"step": 16600
|
1302 |
+
},
|
1303 |
+
{
|
1304 |
+
"epoch": 463.89,
|
1305 |
+
"learning_rate": 1.3616683869708658e-05,
|
1306 |
+
"loss": 0.0113,
|
1307 |
+
"step": 16700
|
1308 |
+
},
|
1309 |
+
{
|
1310 |
+
"epoch": 466.67,
|
1311 |
+
"learning_rate": 1.1614654919452406e-05,
|
1312 |
+
"loss": 0.0117,
|
1313 |
+
"step": 16800
|
1314 |
+
},
|
1315 |
+
{
|
1316 |
+
"epoch": 469.44,
|
1317 |
+
"learning_rate": 9.770015053337078e-06,
|
1318 |
+
"loss": 0.0112,
|
1319 |
+
"step": 16900
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 472.22,
|
1323 |
+
"learning_rate": 8.083358732646206e-06,
|
1324 |
+
"loss": 0.0115,
|
1325 |
+
"step": 17000
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 472.22,
|
1329 |
+
"eval_loss": 0.6556624174118042,
|
1330 |
+
"eval_runtime": 132.4623,
|
1331 |
+
"eval_samples_per_second": 19.696,
|
1332 |
+
"eval_steps_per_second": 0.249,
|
1333 |
+
"eval_wer": 0.4069360483614381,
|
1334 |
+
"step": 17000
|
1335 |
+
},
|
1336 |
+
{
|
1337 |
+
"epoch": 475.0,
|
1338 |
+
"learning_rate": 6.555229506231608e-06,
|
1339 |
+
"loss": 0.0111,
|
1340 |
+
"step": 17100
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 477.78,
|
1344 |
+
"learning_rate": 5.186119835347169e-06,
|
1345 |
+
"loss": 0.0118,
|
1346 |
+
"step": 17200
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 480.56,
|
1350 |
+
"learning_rate": 3.976470934946075e-06,
|
1351 |
+
"loss": 0.0112,
|
1352 |
+
"step": 17300
|
1353 |
+
},
|
1354 |
+
{
|
1355 |
+
"epoch": 483.33,
|
1356 |
+
"learning_rate": 2.92667263149321e-06,
|
1357 |
+
"loss": 0.0117,
|
1358 |
+
"step": 17400
|
1359 |
+
},
|
1360 |
+
{
|
1361 |
+
"epoch": 486.11,
|
1362 |
+
"learning_rate": 2.037063237338044e-06,
|
1363 |
+
"loss": 0.0111,
|
1364 |
+
"step": 17500
|
1365 |
+
},
|
1366 |
+
{
|
1367 |
+
"epoch": 486.11,
|
1368 |
+
"eval_loss": 0.6513079404830933,
|
1369 |
+
"eval_runtime": 131.4726,
|
1370 |
+
"eval_samples_per_second": 19.844,
|
1371 |
+
"eval_steps_per_second": 0.251,
|
1372 |
+
"eval_wer": 0.4059497295577474,
|
1373 |
+
"step": 17500
|
1374 |
+
},
|
1375 |
+
{
|
1376 |
+
"epoch": 488.89,
|
1377 |
+
"learning_rate": 1.3144256109794418e-06,
|
1378 |
+
"loss": 0.0109,
|
1379 |
+
"step": 17600
|
1380 |
+
},
|
1381 |
+
{
|
1382 |
+
"epoch": 491.67,
|
1383 |
+
"learning_rate": 7.44394288673067e-07,
|
1384 |
+
"loss": 0.0112,
|
1385 |
+
"step": 17700
|
1386 |
+
},
|
1387 |
+
{
|
1388 |
+
"epoch": 494.44,
|
1389 |
+
"learning_rate": 3.352551457218578e-07,
|
1390 |
+
"loss": 0.0113,
|
1391 |
+
"step": 17800
|
1392 |
+
},
|
1393 |
+
{
|
1394 |
+
"epoch": 497.22,
|
1395 |
+
"learning_rate": 8.714003300058781e-08,
|
1396 |
+
"loss": 0.011,
|
1397 |
+
"step": 17900
|
1398 |
+
},
|
1399 |
+
{
|
1400 |
+
"epoch": 500.0,
|
1401 |
+
"learning_rate": 1.2890911316176812e-10,
|
1402 |
+
"loss": 0.0113,
|
1403 |
+
"step": 18000
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 500.0,
|
1407 |
+
"eval_loss": 0.6521313190460205,
|
1408 |
+
"eval_runtime": 132.4384,
|
1409 |
+
"eval_samples_per_second": 19.7,
|
1410 |
+
"eval_steps_per_second": 0.249,
|
1411 |
+
"eval_wer": 0.40601336302895324,
|
1412 |
+
"step": 18000
|
1413 |
+
},
|
1414 |
+
{
|
1415 |
+
"epoch": 500.0,
|
1416 |
+
"step": 18000,
|
1417 |
+
"total_flos": 5.3110650126518e+20,
|
1418 |
+
"train_loss": 0.11533763631184896,
|
1419 |
+
"train_runtime": 176050.2174,
|
1420 |
+
"train_samples_per_second": 16.203,
|
1421 |
+
"train_steps_per_second": 0.102
|
1422 |
+
}
|
1423 |
+
],
|
1424 |
+
"max_steps": 18000,
|
1425 |
+
"num_train_epochs": 500,
|
1426 |
+
"total_flos": 5.3110650126518e+20,
|
1427 |
+
"trial_name": null,
|
1428 |
+
"trial_params": null
|
1429 |
+
}
|
wandb/run-20220126_105847-1xdiy2kf/files/config.yaml
CHANGED
@@ -4802,6 +4802,26 @@ _wandb:
|
|
4802 |
5: 1
|
4803 |
6:
|
4804 |
- 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4805 |
python_version: 3.9.6
|
4806 |
start_time: 1643212727
|
4807 |
t:
|
|
|
4802 |
5: 1
|
4803 |
6:
|
4804 |
- 1
|
4805 |
+
- 1: train/train_runtime
|
4806 |
+
5: 1
|
4807 |
+
6:
|
4808 |
+
- 1
|
4809 |
+
- 1: train/train_samples_per_second
|
4810 |
+
5: 1
|
4811 |
+
6:
|
4812 |
+
- 1
|
4813 |
+
- 1: train/train_steps_per_second
|
4814 |
+
5: 1
|
4815 |
+
6:
|
4816 |
+
- 1
|
4817 |
+
- 1: train/total_flos
|
4818 |
+
5: 1
|
4819 |
+
6:
|
4820 |
+
- 1
|
4821 |
+
- 1: train/train_loss
|
4822 |
+
5: 1
|
4823 |
+
6:
|
4824 |
+
- 1
|
4825 |
python_version: 3.9.6
|
4826 |
start_time: 1643212727
|
4827 |
t:
|
wandb/run-20220126_105847-1xdiy2kf/files/output.log
CHANGED
@@ -19556,3 +19556,49 @@ Deleting older checkpoint [checkpoint-17000] due to args.save_total_limitt-17500
|
|
19556 |
Configuration saved in ./checkpoint-18000/config.jsonpoint to ./checkpoint-18000ion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.h..
|
19557 |
Configuration saved in ./checkpoint-18000/preprocessor_config.jsoneckpoint-18000ion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.h..
|
19558 |
Configuration saved in ./preprocessor_config.jsonessor_config.jsoneckpoint-18000ion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.h..
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19556 |
Configuration saved in ./checkpoint-18000/config.jsonpoint to ./checkpoint-18000ion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.h..
|
19557 |
Configuration saved in ./checkpoint-18000/preprocessor_config.jsoneckpoint-18000ion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.h..
|
19558 |
Configuration saved in ./preprocessor_config.jsonessor_config.jsoneckpoint-18000ion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.h..
|
19559 |
+
Configuration saved in ./config.json.78s/it]our model on huggingface.co/models =)on set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.h..
|
19560 |
+
Batch size = 802609ion *****valuation set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19561 |
+
Batch size = 802609ion *****valuation set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19562 |
+
{'eval_loss': 0.6521313190460205, 'eval_wer': 0.40601336302895324, 'eval_runtime': 132.4384, 'eval_samples_per_second': 19.7, 'eval_steps_per_second': 0.249, 'epoch': 500.0}
|
19563 |
+
{'train_runtime': 176050.2174, 'train_samples_per_second': 16.203, 'train_steps_per_second': 0.102, 'train_loss': 0.11533763631184896, 'epoch': 500.0}
|
19564 |
+
***** train metrics *****
|
19565 |
+
epoch = 500.0
|
19566 |
+
train_loss = 0.1153
|
19567 |
+
train_runtime = 2 days, 0:54:10.21
|
19568 |
+
train_samples = 5705
|
19569 |
+
train_samples_per_second = 16.203
|
19570 |
+
train_steps_per_second = 0.102
|
19571 |
+
0% 0/33 [00:00<?, ?it/s]****valuation set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19572 |
+
6% 2/33 [00:04<01:09, 2.23s/it]ation set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19573 |
+
9% 3/33 [00:08<01:34, 3.14s/it]ation set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19574 |
+
12% 4/33 [00:12<01:40, 3.47s/it]ation set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19575 |
+
15% 5/33 [00:17<01:43, 3.69s/it]ation set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19576 |
+
18% 6/33 [00:21<01:44, 3.85s/it]ation set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19577 |
+
21% 7/33 [00:24<01:39, 3.84s/it]ation set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19578 |
+
24% 8/33 [00:28<01:36, 3.87s/it]ation set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19579 |
+
27% 9/33 [00:32<01:33, 3.89s/it]ation set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19580 |
+
30% 10/33 [00:37<01:33, 4.09s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19581 |
+
33% 11/33 [00:41<01:29, 4.06s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19582 |
+
36% 12/33 [00:45<01:24, 4.03s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19583 |
+
39% 13/33 [00:49<01:19, 3.97s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19584 |
+
42% 14/33 [00:53<01:16, 4.02s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19585 |
+
45% 15/33 [00:57<01:13, 4.06s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19586 |
+
48% 16/33 [01:02<01:11, 4.20s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19587 |
+
52% 17/33 [01:06<01:09, 4.34s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19588 |
+
55% 18/33 [01:10<01:03, 4.26s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19589 |
+
58% 19/33 [01:15<00:59, 4.27s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19590 |
+
61% 20/33 [01:19<00:56, 4.34s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19591 |
+
64% 21/33 [01:24<00:52, 4.39s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19592 |
+
67% 22/33 [01:28<00:48, 4.38s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19593 |
+
70% 23/33 [01:32<00:44, 4.41s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19594 |
+
73% 24/33 [01:37<00:39, 4.40s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19595 |
+
76% 25/33 [01:41<00:35, 4.44s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19596 |
+
79% 26/33 [01:46<00:30, 4.39s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19597 |
+
82% 27/33 [01:50<00:26, 4.35s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19598 |
+
85% 28/33 [01:54<00:21, 4.38s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19599 |
+
88% 29/33 [01:58<00:16, 4.13s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19600 |
+
91% 30/33 [02:01<00:11, 3.73s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19601 |
+
94% 31/33 [02:03<00:06, 3.44s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19602 |
+
97% 32/33 [02:06<00:03, 3.19s/it]tion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19603 |
+
Configuration saved in ./config.jsonion set don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
19604 |
+
Configuration saved in ./preprocessor_config.jsont have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.orward` and have been ignored: input_length.h..
|
wandb/run-20220126_105847-1xdiy2kf/files/wandb-summary.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
wandb/run-20220126_105847-1xdiy2kf/logs/debug-internal.log
CHANGED
@@ -50270,3 +50270,80 @@ requests.exceptions.ReadTimeout: HTTPSConnectionPool(host='api.wandb.ai', port=4
|
|
50270 |
2022-01-28 11:52:36,667 DEBUG SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
|
50271 |
2022-01-28 11:52:51,822 DEBUG HandlerThread:2220828 [handler.py:handle_request():130] handle_request: stop_status
|
50272 |
2022-01-28 11:52:51,823 DEBUG SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50270 |
2022-01-28 11:52:36,667 DEBUG SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
|
50271 |
2022-01-28 11:52:51,822 DEBUG HandlerThread:2220828 [handler.py:handle_request():130] handle_request: stop_status
|
50272 |
2022-01-28 11:52:51,823 DEBUG SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
|
50273 |
+
2022-01-28 11:52:57,214 DEBUG SenderThread:2220828 [sender.py:send():234] send: metric
|
50274 |
+
2022-01-28 11:52:57,220 DEBUG SenderThread:2220828 [sender.py:send():234] send: metric
|
50275 |
+
2022-01-28 11:52:57,225 DEBUG SenderThread:2220828 [sender.py:send():234] send: metric
|
50276 |
+
2022-01-28 11:52:57,231 DEBUG SenderThread:2220828 [sender.py:send():234] send: metric
|
50277 |
+
2022-01-28 11:52:57,236 DEBUG SenderThread:2220828 [sender.py:send():234] send: metric
|
50278 |
+
2022-01-28 11:52:57,240 DEBUG SenderThread:2220828 [sender.py:send():234] send: history
|
50279 |
+
2022-01-28 11:52:57,241 DEBUG SenderThread:2220828 [sender.py:send():234] send: summary
|
50280 |
+
2022-01-28 11:52:57,276 INFO SenderThread:2220828 [sender.py:_save_file():939] saving file wandb-summary.json with policy end
|
50281 |
+
2022-01-28 11:52:57,795 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50282 |
+
2022-01-28 11:52:57,795 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/wandb-summary.json
|
50283 |
+
2022-01-28 11:52:59,446 DEBUG SenderThread:2220828 [sender.py:send():234] send: stats
|
50284 |
+
2022-01-28 11:53:03,798 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50285 |
+
2022-01-28 11:53:04,798 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50286 |
+
2022-01-28 11:53:06,982 DEBUG HandlerThread:2220828 [handler.py:handle_request():130] handle_request: stop_status
|
50287 |
+
2022-01-28 11:53:06,984 DEBUG SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
|
50288 |
+
2022-01-28 11:53:09,800 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50289 |
+
2022-01-28 11:53:13,802 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50290 |
+
2022-01-28 11:53:17,804 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50291 |
+
2022-01-28 11:53:21,806 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50292 |
+
2022-01-28 11:53:22,308 DEBUG HandlerThread:2220828 [handler.py:handle_request():130] handle_request: stop_status
|
50293 |
+
2022-01-28 11:53:22,308 DEBUG SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
|
50294 |
+
2022-01-28 11:53:26,808 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50295 |
+
2022-01-28 11:53:28,808 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/config.yaml
|
50296 |
+
2022-01-28 11:53:30,441 DEBUG SenderThread:2220828 [sender.py:send():234] send: stats
|
50297 |
+
2022-01-28 11:53:30,809 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50298 |
+
2022-01-28 11:53:34,811 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50299 |
+
2022-01-28 11:53:37,551 DEBUG HandlerThread:2220828 [handler.py:handle_request():130] handle_request: stop_status
|
50300 |
+
2022-01-28 11:53:37,552 DEBUG SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
|
50301 |
+
2022-01-28 11:53:38,813 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50302 |
+
2022-01-28 11:53:42,815 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50303 |
+
2022-01-28 11:53:46,817 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50304 |
+
2022-01-28 11:53:50,818 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50305 |
+
2022-01-28 11:53:52,744 DEBUG HandlerThread:2220828 [handler.py:handle_request():130] handle_request: stop_status
|
50306 |
+
2022-01-28 11:53:52,744 DEBUG SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
|
50307 |
+
2022-01-28 11:53:54,820 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50308 |
+
2022-01-28 11:53:58,822 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50309 |
+
2022-01-28 11:54:01,408 DEBUG SenderThread:2220828 [sender.py:send():234] send: stats
|
50310 |
+
2022-01-28 11:54:02,824 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50311 |
+
2022-01-28 11:54:06,826 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50312 |
+
2022-01-28 11:54:07,921 DEBUG HandlerThread:2220828 [handler.py:handle_request():130] handle_request: stop_status
|
50313 |
+
2022-01-28 11:54:07,922 DEBUG SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
|
50314 |
+
2022-01-28 11:54:10,828 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50315 |
+
2022-01-28 11:54:14,829 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50316 |
+
2022-01-28 11:54:18,831 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50317 |
+
2022-01-28 11:54:23,170 DEBUG HandlerThread:2220828 [handler.py:handle_request():130] handle_request: stop_status
|
50318 |
+
2022-01-28 11:54:23,170 DEBUG SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
|
50319 |
+
2022-01-28 11:54:25,834 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50320 |
+
2022-01-28 11:54:29,836 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50321 |
+
2022-01-28 11:54:32,405 DEBUG SenderThread:2220828 [sender.py:send():234] send: stats
|
50322 |
+
2022-01-28 11:54:33,838 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50323 |
+
2022-01-28 11:54:37,839 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50324 |
+
2022-01-28 11:54:38,394 DEBUG HandlerThread:2220828 [handler.py:handle_request():130] handle_request: stop_status
|
50325 |
+
2022-01-28 11:54:38,394 DEBUG SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
|
50326 |
+
2022-01-28 11:54:41,841 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50327 |
+
2022-01-28 11:54:47,844 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50328 |
+
2022-01-28 11:54:51,845 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50329 |
+
2022-01-28 11:54:53,583 DEBUG HandlerThread:2220828 [handler.py:handle_request():130] handle_request: stop_status
|
50330 |
+
2022-01-28 11:54:53,583 DEBUG SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
|
50331 |
+
2022-01-28 11:54:55,847 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50332 |
+
2022-01-28 11:54:59,849 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50333 |
+
2022-01-28 11:55:03,399 DEBUG SenderThread:2220828 [sender.py:send():234] send: stats
|
50334 |
+
2022-01-28 11:55:03,851 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50335 |
+
2022-01-28 11:55:07,853 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50336 |
+
2022-01-28 11:55:08,733 DEBUG HandlerThread:2220828 [handler.py:handle_request():130] handle_request: stop_status
|
50337 |
+
2022-01-28 11:55:08,734 DEBUG SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
|
50338 |
+
2022-01-28 11:55:09,854 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50339 |
+
2022-01-28 11:55:13,855 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50340 |
+
2022-01-28 11:55:15,856 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50341 |
+
2022-01-28 11:55:17,392 DEBUG SenderThread:2220828 [sender.py:send():234] send: history
|
50342 |
+
2022-01-28 11:55:17,416 DEBUG SenderThread:2220828 [sender.py:send():234] send: summary
|
50343 |
+
2022-01-28 11:55:17,454 INFO SenderThread:2220828 [sender.py:_save_file():939] saving file wandb-summary.json with policy end
|
50344 |
+
2022-01-28 11:55:17,857 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50345 |
+
2022-01-28 11:55:17,858 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/wandb-summary.json
|
50346 |
+
2022-01-28 11:55:23,949 DEBUG HandlerThread:2220828 [handler.py:handle_request():130] handle_request: stop_status
|
50347 |
+
2022-01-28 11:55:23,950 DEBUG SenderThread:2220828 [sender.py:send_request():248] send_request: stop_status
|
50348 |
+
2022-01-28 11:55:25,861 INFO Thread-8 :2220828 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220126_105847-1xdiy2kf/files/output.log
|
50349 |
+
2022-01-28 11:55:34,430 DEBUG SenderThread:2220828 [sender.py:send():234] send: stats
|
wandb/run-20220126_105847-1xdiy2kf/run-1xdiy2kf.wandb
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7e665cf3bd1d21f24efc603dcc4e99707b7439674c0638bb608c504f3187318
|
3 |
+
size 124718462
|