End of training
Browse files
all_results.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_loss":
|
4 |
-
"eval_runtime":
|
5 |
-
"eval_samples_per_second": 1.
|
6 |
-
"eval_steps_per_second": 0.
|
7 |
-
"eval_wer":
|
8 |
-
"train_loss": 0.
|
9 |
-
"train_runtime":
|
10 |
-
"train_samples_per_second":
|
11 |
-
"train_steps_per_second": 0.
|
12 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 14.81,
|
3 |
+
"eval_loss": 1.0876343250274658,
|
4 |
+
"eval_runtime": 430.2181,
|
5 |
+
"eval_samples_per_second": 1.19,
|
6 |
+
"eval_steps_per_second": 0.149,
|
7 |
+
"eval_wer": 57.99031476997578,
|
8 |
+
"train_loss": 0.027764302641153336,
|
9 |
+
"train_runtime": 533.3671,
|
10 |
+
"train_samples_per_second": 11.999,
|
11 |
+
"train_steps_per_second": 0.75
|
12 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_loss":
|
4 |
-
"eval_runtime":
|
5 |
-
"eval_samples_per_second": 1.
|
6 |
-
"eval_steps_per_second": 0.
|
7 |
-
"eval_wer":
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 14.81,
|
3 |
+
"eval_loss": 1.0876343250274658,
|
4 |
+
"eval_runtime": 430.2181,
|
5 |
+
"eval_samples_per_second": 1.19,
|
6 |
+
"eval_steps_per_second": 0.149,
|
7 |
+
"eval_wer": 57.99031476997578
|
8 |
}
|
runs/Dec16_17-19-03_129-146-104-29/events.out.tfevents.1671212207.129-146-104-29.135044.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:545ca5771a8154efb26456674ebf33295afb6a4555ae3ab78fbb7408a45d757c
|
3 |
+
size 358
|
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": 14.81,
|
3 |
+
"train_loss": 0.027764302641153336,
|
4 |
+
"train_runtime": 533.3671,
|
5 |
+
"train_samples_per_second": 11.999,
|
6 |
+
"train_steps_per_second": 0.75
|
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 +107,87 @@
|
|
107 |
"step": 300
|
108 |
},
|
109 |
{
|
110 |
-
"epoch": 11.
|
111 |
-
"
|
112 |
-
"
|
113 |
-
"
|
114 |
-
|
115 |
-
|
116 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
117 |
}
|
118 |
],
|
119 |
-
"max_steps":
|
120 |
-
"num_train_epochs":
|
121 |
-
"total_flos": 1.
|
122 |
"trial_name": null,
|
123 |
"trial_params": null
|
124 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 57.99031476997578,
|
3 |
+
"best_model_checkpoint": "./checkpoint-400",
|
4 |
+
"epoch": 14.814814814814815,
|
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": 11.48,
|
111 |
+
"learning_rate": 6.120000000000001e-06,
|
112 |
+
"loss": 0.1991,
|
113 |
+
"step": 310
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 11.85,
|
117 |
+
"learning_rate": 6.3200000000000005e-06,
|
118 |
+
"loss": 0.1798,
|
119 |
+
"step": 320
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 12.22,
|
123 |
+
"learning_rate": 6.520000000000001e-06,
|
124 |
+
"loss": 0.1426,
|
125 |
+
"step": 330
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 12.59,
|
129 |
+
"learning_rate": 6.720000000000001e-06,
|
130 |
+
"loss": 0.125,
|
131 |
+
"step": 340
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 12.96,
|
135 |
+
"learning_rate": 6.92e-06,
|
136 |
+
"loss": 0.1177,
|
137 |
+
"step": 350
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 13.33,
|
141 |
+
"learning_rate": 7.1200000000000004e-06,
|
142 |
+
"loss": 0.0874,
|
143 |
+
"step": 360
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 13.7,
|
147 |
+
"learning_rate": 7.32e-06,
|
148 |
+
"loss": 0.0852,
|
149 |
+
"step": 370
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 14.07,
|
153 |
+
"learning_rate": 7.520000000000001e-06,
|
154 |
+
"loss": 0.0666,
|
155 |
+
"step": 380
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 14.44,
|
159 |
+
"learning_rate": 7.72e-06,
|
160 |
+
"loss": 0.0531,
|
161 |
+
"step": 390
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 14.81,
|
165 |
+
"learning_rate": 7.92e-06,
|
166 |
+
"loss": 0.054,
|
167 |
+
"step": 400
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 14.81,
|
171 |
+
"eval_loss": 1.0876343250274658,
|
172 |
+
"eval_runtime": 428.9567,
|
173 |
+
"eval_samples_per_second": 1.194,
|
174 |
+
"eval_steps_per_second": 0.149,
|
175 |
+
"eval_wer": 57.99031476997578,
|
176 |
+
"step": 400
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 14.81,
|
180 |
+
"step": 400,
|
181 |
+
"total_flos": 1.84290636644352e+18,
|
182 |
+
"train_loss": 0.027764302641153336,
|
183 |
+
"train_runtime": 533.3671,
|
184 |
+
"train_samples_per_second": 11.999,
|
185 |
+
"train_steps_per_second": 0.75
|
186 |
}
|
187 |
],
|
188 |
+
"max_steps": 400,
|
189 |
+
"num_train_epochs": 15,
|
190 |
+
"total_flos": 1.84290636644352e+18,
|
191 |
"trial_name": null,
|
192 |
"trial_params": null
|
193 |
}
|