Model save
Browse files- all_results.json +5 -5
- preprocessor_config.json +1 -1
- pytorch_model.bin +1 -1
- runs/Oct25_23-09-46_hieu-pc/1666714229.6707256/events.out.tfevents.1666714229.hieu-pc.2701841.1 +3 -0
- runs/Oct25_23-09-46_hieu-pc/events.out.tfevents.1666714229.hieu-pc.2701841.0 +3 -0
- special_tokens_map.json +14 -0
- train_results.json +5 -5
- trainer_state.json +11 -20
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 14.
|
| 3 |
"eval_loss": 3.52602481842041,
|
| 4 |
"eval_runtime": 802.7081,
|
| 5 |
"eval_samples": 198,
|
| 6 |
"eval_samples_per_second": 0.247,
|
| 7 |
"eval_steps_per_second": 0.031,
|
| 8 |
"eval_wer": 1.0,
|
| 9 |
-
"train_loss":
|
| 10 |
-
"train_runtime":
|
| 11 |
"train_samples": 421,
|
| 12 |
-
"train_samples_per_second":
|
| 13 |
-
"train_steps_per_second": 0.
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 14.95,
|
| 3 |
"eval_loss": 3.52602481842041,
|
| 4 |
"eval_runtime": 802.7081,
|
| 5 |
"eval_samples": 198,
|
| 6 |
"eval_samples_per_second": 0.247,
|
| 7 |
"eval_steps_per_second": 0.031,
|
| 8 |
"eval_wer": 1.0,
|
| 9 |
+
"train_loss": 90.87097981770833,
|
| 10 |
+
"train_runtime": 1614.616,
|
| 11 |
"train_samples": 421,
|
| 12 |
+
"train_samples_per_second": 3.911,
|
| 13 |
+
"train_steps_per_second": 0.019
|
| 14 |
}
|
preprocessor_config.json
CHANGED
|
@@ -5,5 +5,5 @@
|
|
| 5 |
"padding_side": "right",
|
| 6 |
"padding_value": 0,
|
| 7 |
"return_attention_mask": true,
|
| 8 |
-
"sampling_rate":
|
| 9 |
}
|
|
|
|
| 5 |
"padding_side": "right",
|
| 6 |
"padding_value": 0,
|
| 7 |
"return_attention_mask": true,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262279985
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98fd5b71bcf0ef3b840c61beb6d75f2cecfeee516902814904d76851d1fb50e0
|
| 3 |
size 1262279985
|
runs/Oct25_23-09-46_hieu-pc/1666714229.6707256/events.out.tfevents.1666714229.hieu-pc.2701841.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2bb86254d300b0877c17a198a3c9a61f705f331e6b110d33f9bd219900abb957
|
| 3 |
+
size 5503
|
runs/Oct25_23-09-46_hieu-pc/events.out.tfevents.1666714229.hieu-pc.2701841.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3b51c226316c450bc4bf45321a8b8e81cd4b89e7e030cd75e4e2b84976aeceb
|
| 3 |
+
size 5688
|
special_tokens_map.json
CHANGED
|
@@ -147,6 +147,20 @@
|
|
| 147 |
"rstrip": false,
|
| 148 |
"single_word": false
|
| 149 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 150 |
{
|
| 151 |
"content": "</s>",
|
| 152 |
"lstrip": false,
|
|
|
|
| 147 |
"rstrip": false,
|
| 148 |
"single_word": false
|
| 149 |
},
|
| 150 |
+
{
|
| 151 |
+
"content": "</s>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"content": "<s>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": true,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false
|
| 163 |
+
},
|
| 164 |
{
|
| 165 |
"content": "</s>",
|
| 166 |
"lstrip": false,
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 14.
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 421,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 14.95,
|
| 3 |
+
"train_loss": 90.87097981770833,
|
| 4 |
+
"train_runtime": 1614.616,
|
| 5 |
"train_samples": 421,
|
| 6 |
+
"train_samples_per_second": 3.911,
|
| 7 |
+
"train_steps_per_second": 0.019
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,34 +1,25 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 14.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
-
"epoch":
|
| 12 |
-
"
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"
|
| 17 |
-
"
|
| 18 |
-
},
|
| 19 |
-
{
|
| 20 |
-
"epoch": 14.96,
|
| 21 |
-
"step": 195,
|
| 22 |
-
"total_flos": 2.4406399452562217e+18,
|
| 23 |
-
"train_loss": 29.569411057692307,
|
| 24 |
-
"train_runtime": 58895.0409,
|
| 25 |
-
"train_samples_per_second": 0.107,
|
| 26 |
-
"train_steps_per_second": 0.003
|
| 27 |
}
|
| 28 |
],
|
| 29 |
-
"max_steps":
|
| 30 |
"num_train_epochs": 15,
|
| 31 |
-
"total_flos": 2.
|
| 32 |
"trial_name": null,
|
| 33 |
"trial_params": null
|
| 34 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 14.950118764845605,
|
| 5 |
+
"global_step": 30,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 14.95,
|
| 12 |
+
"step": 30,
|
| 13 |
+
"total_flos": 2.1433299350446886e+18,
|
| 14 |
+
"train_loss": 90.87097981770833,
|
| 15 |
+
"train_runtime": 1614.616,
|
| 16 |
+
"train_samples_per_second": 3.911,
|
| 17 |
+
"train_steps_per_second": 0.019
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
}
|
| 19 |
],
|
| 20 |
+
"max_steps": 30,
|
| 21 |
"num_train_epochs": 15,
|
| 22 |
+
"total_flos": 2.1433299350446886e+18,
|
| 23 |
"trial_name": null,
|
| 24 |
"trial_params": null
|
| 25 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3375
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ebfbff26a425274ed2fb8c8c9f495a9431f217d229b437e2db96c001d9be58f
|
| 3 |
size 3375
|