Training in progress, step 500
Browse files- all_results.json +5 -5
- pytorch_model.bin +1 -1
- run.sh +1 -1
- runs/Dec14_11-06-21_129-213-22-31/1671016001.2088182/events.out.tfevents.1671016001.129-213-22-31.79356.1 +3 -0
- runs/Dec14_11-06-21_129-213-22-31/events.out.tfevents.1671016001.129-213-22-31.79356.0 +3 -0
- train_results.json +5 -5
- trainer_state.json +47 -14
- training_args.bin +1 -1
all_results.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
"eval_loss": 1.1061279773712158,
|
4 |
"eval_runtime": 1526.712,
|
5 |
"eval_samples_per_second": 0.335,
|
6 |
"eval_steps_per_second": 0.021,
|
7 |
"eval_wer": 67.83942963422194,
|
8 |
-
"train_loss": 0.
|
9 |
-
"train_runtime":
|
10 |
-
"train_samples_per_second":
|
11 |
-
"train_steps_per_second": 0.
|
12 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 57.14,
|
3 |
"eval_loss": 1.1061279773712158,
|
4 |
"eval_runtime": 1526.712,
|
5 |
"eval_samples_per_second": 0.335,
|
6 |
"eval_steps_per_second": 0.021,
|
7 |
"eval_wer": 67.83942963422194,
|
8 |
+
"train_loss": 0.2256472110748291,
|
9 |
+
"train_runtime": 2414.0721,
|
10 |
+
"train_samples_per_second": 10.604,
|
11 |
+
"train_steps_per_second": 0.166
|
12 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3055754841
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93fb77ff4be7d131dc72a59ae8749fc812f33ecdb870c3a6a640cd40270398aa
|
3 |
size 3055754841
|
run.sh
CHANGED
@@ -6,7 +6,7 @@ python run_speech_recognition_seq2seq_streaming.py \
|
|
6 |
--train_split_name="train+validation" \
|
7 |
--eval_split_name="test" \
|
8 |
--model_index_name="Whisper Medium Pashto" \
|
9 |
-
--max_steps="
|
10 |
--output_dir="./" \
|
11 |
--per_device_train_batch_size="32" \
|
12 |
--per_device_eval_batch_size="16" \
|
|
|
6 |
--train_split_name="train+validation" \
|
7 |
--eval_split_name="test" \
|
8 |
--model_index_name="Whisper Medium Pashto" \
|
9 |
+
--max_steps="500" \
|
10 |
--output_dir="./" \
|
11 |
--per_device_train_batch_size="32" \
|
12 |
--per_device_eval_batch_size="16" \
|
runs/Dec14_11-06-21_129-213-22-31/1671016001.2088182/events.out.tfevents.1671016001.129-213-22-31.79356.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6adceedc77ad7fefd09909d8b64b67eebb961a1e32af38007ccb2ceff1aafebd
|
3 |
+
size 5869
|
runs/Dec14_11-06-21_129-213-22-31/events.out.tfevents.1671016001.129-213-22-31.79356.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6496be6ec99235861eeb9b63130807ad2b2d1494c7a96b80f055ce83d44bac3
|
3 |
+
size 5211
|
train_results.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples_per_second":
|
6 |
-
"train_steps_per_second": 0.
|
7 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 57.14,
|
3 |
+
"train_loss": 0.2256472110748291,
|
4 |
+
"train_runtime": 2414.0721,
|
5 |
+
"train_samples_per_second": 10.604,
|
6 |
+
"train_steps_per_second": 0.166
|
7 |
}
|
trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
-
"best_model_checkpoint": "./checkpoint-
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -107,18 +107,51 @@
|
|
107 |
"step": 300
|
108 |
},
|
109 |
{
|
110 |
-
"epoch":
|
111 |
-
"
|
112 |
-
"
|
113 |
-
"
|
114 |
-
|
115 |
-
|
116 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
117 |
}
|
118 |
],
|
119 |
-
"max_steps":
|
120 |
-
"num_train_epochs":
|
121 |
-
"total_flos":
|
122 |
"trial_name": null,
|
123 |
"trial_params": null
|
124 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 66.42901425914445,
|
3 |
+
"best_model_checkpoint": "./checkpoint-400",
|
4 |
+
"epoch": 57.142857142857146,
|
5 |
+
"global_step": 400,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
107 |
"step": 300
|
108 |
},
|
109 |
{
|
110 |
+
"epoch": 46.43,
|
111 |
+
"learning_rate": 6e-08,
|
112 |
+
"loss": 0.919,
|
113 |
+
"step": 325
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 50.0,
|
117 |
+
"learning_rate": 4.076923076923077e-08,
|
118 |
+
"loss": 0.9097,
|
119 |
+
"step": 350
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 53.57,
|
123 |
+
"learning_rate": 2.1538461538461537e-08,
|
124 |
+
"loss": 0.8935,
|
125 |
+
"step": 375
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 57.14,
|
129 |
+
"learning_rate": 2.3076923076923076e-09,
|
130 |
+
"loss": 0.8882,
|
131 |
+
"step": 400
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 57.14,
|
135 |
+
"eval_loss": 1.0769362449645996,
|
136 |
+
"eval_runtime": 1533.1785,
|
137 |
+
"eval_samples_per_second": 0.334,
|
138 |
+
"eval_steps_per_second": 0.021,
|
139 |
+
"eval_wer": 66.42901425914445,
|
140 |
+
"step": 400
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 57.14,
|
144 |
+
"step": 400,
|
145 |
+
"total_flos": 2.513851947712512e+19,
|
146 |
+
"train_loss": 0.2256472110748291,
|
147 |
+
"train_runtime": 2414.0721,
|
148 |
+
"train_samples_per_second": 10.604,
|
149 |
+
"train_steps_per_second": 0.166
|
150 |
}
|
151 |
],
|
152 |
+
"max_steps": 400,
|
153 |
+
"num_train_epochs": 58,
|
154 |
+
"total_flos": 2.513851947712512e+19,
|
155 |
"trial_name": null,
|
156 |
"trial_params": null
|
157 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3579
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c124a7507e0b7490e416734b5493bfea9066395093cc411ab4e36fd2953b0c1c
|
3 |
size 3579
|