"auto-commit"
Browse files- model-bin/finetune/base/{checkpoint-26377 → checkpoint-26999}/config.json +0 -0
- model-bin/finetune/base/{checkpoint-26377 → checkpoint-26999}/optimizer.pt +1 -1
- model-bin/finetune/base/{checkpoint-26377 → checkpoint-26999}/preprocessor_config.json +0 -0
- model-bin/finetune/base/{checkpoint-26377 → checkpoint-26999}/pytorch_model.bin +1 -1
- model-bin/finetune/base/{checkpoint-26377 → checkpoint-26999}/rng_state.pth +1 -1
- model-bin/finetune/base/{checkpoint-26377 → checkpoint-26999}/scaler.pt +1 -1
- model-bin/finetune/base/{checkpoint-26377 → checkpoint-26999}/scheduler.pt +1 -1
- model-bin/finetune/base/{checkpoint-26377 → checkpoint-26999}/trainer_state.json +421 -4
- model-bin/finetune/base/{checkpoint-26377 → checkpoint-26999}/training_args.bin +0 -0
- model-bin/finetune/base/log/1629611321.118057/events.out.tfevents.1629611321.91f414e9573a.903.61 +3 -0
- model-bin/finetune/base/log/1629611966.8683221/events.out.tfevents.1629611966.91f414e9573a.903.63 +3 -0
- model-bin/finetune/base/log/1629612621.1430087/events.out.tfevents.1629612621.91f414e9573a.903.65 +3 -0
- model-bin/finetune/base/log/1629613282.6240292/events.out.tfevents.1629613282.91f414e9573a.903.67 +3 -0
- model-bin/finetune/base/log/1629614041.3431811/events.out.tfevents.1629614041.91f414e9573a.903.69 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629611321.91f414e9573a.903.60 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629611966.91f414e9573a.903.62 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629612621.91f414e9573a.903.64 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629613282.91f414e9573a.903.66 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629614041.91f414e9573a.903.68 +3 -0
model-bin/finetune/base/{checkpoint-26377 → checkpoint-26999}/config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-26377 → checkpoint-26999}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 722165009
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb36c03631893636b8a8e6ee35f28ed9e1af1d733f6b468839d5b1a0f1db05cf
|
| 3 |
size 722165009
|
model-bin/finetune/base/{checkpoint-26377 → checkpoint-26999}/preprocessor_config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-26377 → checkpoint-26999}/pytorch_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 377909911
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:468cad1c841b84b310b0ca37932ae0961490292a62aea256e9fdf269e9696637
|
| 3 |
size 377909911
|
model-bin/finetune/base/{checkpoint-26377 → checkpoint-26999}/rng_state.pth
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8576044903d37a68285d1a04f83c7e8f2ff175f51030a71db74a639a131735f
|
| 3 |
size 14503
|
model-bin/finetune/base/{checkpoint-26377 → checkpoint-26999}/scaler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 559
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d935897856e3f77525bde7b426f3c8dff5bc10c60c3c652fda29eb83c956c256
|
| 3 |
size 559
|
model-bin/finetune/base/{checkpoint-26377 → checkpoint-26999}/scheduler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:126d6a6507a44d67b65d12bc7e40360277333b7cb61c32127829673ba9d70885
|
| 3 |
size 623
|
model-bin/finetune/base/{checkpoint-26377 → checkpoint-26999}/trainer_state.json
RENAMED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2158154859967051,
|
| 3 |
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-25631",
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -140016,11 +140016,428 @@
|
|
| 140016 |
"eval_steps_per_second": 0.663,
|
| 140017 |
"eval_wer": 0.23124177270732776,
|
| 140018 |
"step": 26377
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 140019 |
}
|
| 140020 |
],
|
| 140021 |
-
"max_steps":
|
| 140022 |
"num_train_epochs": 5000,
|
| 140023 |
-
"total_flos": 7.
|
| 140024 |
"trial_name": null,
|
| 140025 |
"trial_params": null
|
| 140026 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2158154859967051,
|
| 3 |
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-25631",
|
| 4 |
+
"epoch": 215.0,
|
| 5 |
+
"global_step": 26999,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 140016 |
"eval_steps_per_second": 0.663,
|
| 140017 |
"eval_wer": 0.23124177270732776,
|
| 140018 |
"step": 26377
|
| 140019 |
+
},
|
| 140020 |
+
{
|
| 140021 |
+
"epoch": 212.02,
|
| 140022 |
+
"learning_rate": 9.590145395799678e-06,
|
| 140023 |
+
"loss": 0.4772,
|
| 140024 |
+
"step": 26380
|
| 140025 |
+
},
|
| 140026 |
+
{
|
| 140027 |
+
"epoch": 212.1,
|
| 140028 |
+
"learning_rate": 9.589983844911148e-06,
|
| 140029 |
+
"loss": 0.4487,
|
| 140030 |
+
"step": 26390
|
| 140031 |
+
},
|
| 140032 |
+
{
|
| 140033 |
+
"epoch": 212.18,
|
| 140034 |
+
"learning_rate": 9.589822294022618e-06,
|
| 140035 |
+
"loss": 0.724,
|
| 140036 |
+
"step": 26400
|
| 140037 |
+
},
|
| 140038 |
+
{
|
| 140039 |
+
"epoch": 212.27,
|
| 140040 |
+
"learning_rate": 9.589660743134088e-06,
|
| 140041 |
+
"loss": 0.8054,
|
| 140042 |
+
"step": 26410
|
| 140043 |
+
},
|
| 140044 |
+
{
|
| 140045 |
+
"epoch": 212.35,
|
| 140046 |
+
"learning_rate": 9.589499192245558e-06,
|
| 140047 |
+
"loss": 0.4439,
|
| 140048 |
+
"step": 26420
|
| 140049 |
+
},
|
| 140050 |
+
{
|
| 140051 |
+
"epoch": 212.43,
|
| 140052 |
+
"learning_rate": 9.589337641357028e-06,
|
| 140053 |
+
"loss": 1.0191,
|
| 140054 |
+
"step": 26430
|
| 140055 |
+
},
|
| 140056 |
+
{
|
| 140057 |
+
"epoch": 212.51,
|
| 140058 |
+
"learning_rate": 9.589176090468498e-06,
|
| 140059 |
+
"loss": 0.3906,
|
| 140060 |
+
"step": 26440
|
| 140061 |
+
},
|
| 140062 |
+
{
|
| 140063 |
+
"epoch": 212.59,
|
| 140064 |
+
"learning_rate": 9.589014539579968e-06,
|
| 140065 |
+
"loss": 0.7023,
|
| 140066 |
+
"step": 26450
|
| 140067 |
+
},
|
| 140068 |
+
{
|
| 140069 |
+
"epoch": 212.67,
|
| 140070 |
+
"learning_rate": 9.588852988691438e-06,
|
| 140071 |
+
"loss": 0.8464,
|
| 140072 |
+
"step": 26460
|
| 140073 |
+
},
|
| 140074 |
+
{
|
| 140075 |
+
"epoch": 212.75,
|
| 140076 |
+
"learning_rate": 9.588691437802908e-06,
|
| 140077 |
+
"loss": 0.5026,
|
| 140078 |
+
"step": 26470
|
| 140079 |
+
},
|
| 140080 |
+
{
|
| 140081 |
+
"epoch": 212.83,
|
| 140082 |
+
"learning_rate": 9.588529886914378e-06,
|
| 140083 |
+
"loss": 1.1228,
|
| 140084 |
+
"step": 26480
|
| 140085 |
+
},
|
| 140086 |
+
{
|
| 140087 |
+
"epoch": 212.91,
|
| 140088 |
+
"learning_rate": 9.588368336025848e-06,
|
| 140089 |
+
"loss": 0.3913,
|
| 140090 |
+
"step": 26490
|
| 140091 |
+
},
|
| 140092 |
+
{
|
| 140093 |
+
"epoch": 212.99,
|
| 140094 |
+
"learning_rate": 9.58820678513732e-06,
|
| 140095 |
+
"loss": 0.8987,
|
| 140096 |
+
"step": 26500
|
| 140097 |
+
},
|
| 140098 |
+
{
|
| 140099 |
+
"epoch": 213.0,
|
| 140100 |
+
"eval_loss": 0.4643515646457672,
|
| 140101 |
+
"eval_runtime": 41.5092,
|
| 140102 |
+
"eval_samples_per_second": 20.357,
|
| 140103 |
+
"eval_steps_per_second": 0.65,
|
| 140104 |
+
"eval_wer": 0.22439278021243408,
|
| 140105 |
+
"step": 26501
|
| 140106 |
+
},
|
| 140107 |
+
{
|
| 140108 |
+
"epoch": 213.07,
|
| 140109 |
+
"learning_rate": 9.58804523424879e-06,
|
| 140110 |
+
"loss": 0.4065,
|
| 140111 |
+
"step": 26510
|
| 140112 |
+
},
|
| 140113 |
+
{
|
| 140114 |
+
"epoch": 213.15,
|
| 140115 |
+
"learning_rate": 9.58788368336026e-06,
|
| 140116 |
+
"loss": 0.4921,
|
| 140117 |
+
"step": 26520
|
| 140118 |
+
},
|
| 140119 |
+
{
|
| 140120 |
+
"epoch": 213.23,
|
| 140121 |
+
"learning_rate": 9.58772213247173e-06,
|
| 140122 |
+
"loss": 1.1417,
|
| 140123 |
+
"step": 26530
|
| 140124 |
+
},
|
| 140125 |
+
{
|
| 140126 |
+
"epoch": 213.31,
|
| 140127 |
+
"learning_rate": 9.5875605815832e-06,
|
| 140128 |
+
"loss": 0.4404,
|
| 140129 |
+
"step": 26540
|
| 140130 |
+
},
|
| 140131 |
+
{
|
| 140132 |
+
"epoch": 213.4,
|
| 140133 |
+
"learning_rate": 9.58739903069467e-06,
|
| 140134 |
+
"loss": 0.8463,
|
| 140135 |
+
"step": 26550
|
| 140136 |
+
},
|
| 140137 |
+
{
|
| 140138 |
+
"epoch": 213.48,
|
| 140139 |
+
"learning_rate": 9.58723747980614e-06,
|
| 140140 |
+
"loss": 0.6186,
|
| 140141 |
+
"step": 26560
|
| 140142 |
+
},
|
| 140143 |
+
{
|
| 140144 |
+
"epoch": 213.56,
|
| 140145 |
+
"learning_rate": 9.58707592891761e-06,
|
| 140146 |
+
"loss": 0.4539,
|
| 140147 |
+
"step": 26570
|
| 140148 |
+
},
|
| 140149 |
+
{
|
| 140150 |
+
"epoch": 213.64,
|
| 140151 |
+
"learning_rate": 9.58691437802908e-06,
|
| 140152 |
+
"loss": 0.9899,
|
| 140153 |
+
"step": 26580
|
| 140154 |
+
},
|
| 140155 |
+
{
|
| 140156 |
+
"epoch": 213.72,
|
| 140157 |
+
"learning_rate": 9.58675282714055e-06,
|
| 140158 |
+
"loss": 0.4162,
|
| 140159 |
+
"step": 26590
|
| 140160 |
+
},
|
| 140161 |
+
{
|
| 140162 |
+
"epoch": 213.8,
|
| 140163 |
+
"learning_rate": 9.58659127625202e-06,
|
| 140164 |
+
"loss": 0.8224,
|
| 140165 |
+
"step": 26600
|
| 140166 |
+
},
|
| 140167 |
+
{
|
| 140168 |
+
"epoch": 213.88,
|
| 140169 |
+
"learning_rate": 9.586429725363491e-06,
|
| 140170 |
+
"loss": 0.5969,
|
| 140171 |
+
"step": 26610
|
| 140172 |
+
},
|
| 140173 |
+
{
|
| 140174 |
+
"epoch": 213.96,
|
| 140175 |
+
"learning_rate": 9.586268174474961e-06,
|
| 140176 |
+
"loss": 0.5126,
|
| 140177 |
+
"step": 26620
|
| 140178 |
+
},
|
| 140179 |
+
{
|
| 140180 |
+
"epoch": 214.0,
|
| 140181 |
+
"eval_loss": 0.4537523686885834,
|
| 140182 |
+
"eval_runtime": 41.1944,
|
| 140183 |
+
"eval_samples_per_second": 20.512,
|
| 140184 |
+
"eval_steps_per_second": 0.655,
|
| 140185 |
+
"eval_wer": 0.21717642002721868,
|
| 140186 |
+
"step": 26625
|
| 140187 |
+
},
|
| 140188 |
+
{
|
| 140189 |
+
"epoch": 213.04,
|
| 140190 |
+
"learning_rate": 9.586106623586431e-06,
|
| 140191 |
+
"loss": 0.4603,
|
| 140192 |
+
"step": 26630
|
| 140193 |
+
},
|
| 140194 |
+
{
|
| 140195 |
+
"epoch": 213.12,
|
| 140196 |
+
"learning_rate": 9.585945072697901e-06,
|
| 140197 |
+
"loss": 0.423,
|
| 140198 |
+
"step": 26640
|
| 140199 |
+
},
|
| 140200 |
+
{
|
| 140201 |
+
"epoch": 213.2,
|
| 140202 |
+
"learning_rate": 9.585783521809371e-06,
|
| 140203 |
+
"loss": 1.0697,
|
| 140204 |
+
"step": 26650
|
| 140205 |
+
},
|
| 140206 |
+
{
|
| 140207 |
+
"epoch": 213.28,
|
| 140208 |
+
"learning_rate": 9.585621970920841e-06,
|
| 140209 |
+
"loss": 0.4518,
|
| 140210 |
+
"step": 26660
|
| 140211 |
+
},
|
| 140212 |
+
{
|
| 140213 |
+
"epoch": 213.36,
|
| 140214 |
+
"learning_rate": 9.585460420032311e-06,
|
| 140215 |
+
"loss": 0.5595,
|
| 140216 |
+
"step": 26670
|
| 140217 |
+
},
|
| 140218 |
+
{
|
| 140219 |
+
"epoch": 213.44,
|
| 140220 |
+
"learning_rate": 9.585298869143781e-06,
|
| 140221 |
+
"loss": 0.9863,
|
| 140222 |
+
"step": 26680
|
| 140223 |
+
},
|
| 140224 |
+
{
|
| 140225 |
+
"epoch": 213.52,
|
| 140226 |
+
"learning_rate": 9.58513731825525e-06,
|
| 140227 |
+
"loss": 0.4273,
|
| 140228 |
+
"step": 26690
|
| 140229 |
+
},
|
| 140230 |
+
{
|
| 140231 |
+
"epoch": 213.6,
|
| 140232 |
+
"learning_rate": 9.58497576736672e-06,
|
| 140233 |
+
"loss": 1.1205,
|
| 140234 |
+
"step": 26700
|
| 140235 |
+
},
|
| 140236 |
+
{
|
| 140237 |
+
"epoch": 213.68,
|
| 140238 |
+
"learning_rate": 9.58481421647819e-06,
|
| 140239 |
+
"loss": 0.4184,
|
| 140240 |
+
"step": 26710
|
| 140241 |
+
},
|
| 140242 |
+
{
|
| 140243 |
+
"epoch": 213.76,
|
| 140244 |
+
"learning_rate": 9.58465266558966e-06,
|
| 140245 |
+
"loss": 0.6096,
|
| 140246 |
+
"step": 26720
|
| 140247 |
+
},
|
| 140248 |
+
{
|
| 140249 |
+
"epoch": 213.84,
|
| 140250 |
+
"learning_rate": 9.584491114701132e-06,
|
| 140251 |
+
"loss": 0.8789,
|
| 140252 |
+
"step": 26730
|
| 140253 |
+
},
|
| 140254 |
+
{
|
| 140255 |
+
"epoch": 213.92,
|
| 140256 |
+
"learning_rate": 9.584329563812602e-06,
|
| 140257 |
+
"loss": 0.6324,
|
| 140258 |
+
"step": 26740
|
| 140259 |
+
},
|
| 140260 |
+
{
|
| 140261 |
+
"epoch": 214.0,
|
| 140262 |
+
"learning_rate": 9.584168012924072e-06,
|
| 140263 |
+
"loss": 1.1419,
|
| 140264 |
+
"step": 26750
|
| 140265 |
+
},
|
| 140266 |
+
{
|
| 140267 |
+
"epoch": 214.0,
|
| 140268 |
+
"eval_loss": 0.4872305691242218,
|
| 140269 |
+
"eval_runtime": 39.5522,
|
| 140270 |
+
"eval_samples_per_second": 21.364,
|
| 140271 |
+
"eval_steps_per_second": 0.683,
|
| 140272 |
+
"eval_wer": 0.22106345475910694,
|
| 140273 |
+
"step": 26750
|
| 140274 |
+
},
|
| 140275 |
+
{
|
| 140276 |
+
"epoch": 215.08,
|
| 140277 |
+
"learning_rate": 9.584006462035542e-06,
|
| 140278 |
+
"loss": 0.4879,
|
| 140279 |
+
"step": 26760
|
| 140280 |
+
},
|
| 140281 |
+
{
|
| 140282 |
+
"epoch": 215.16,
|
| 140283 |
+
"learning_rate": 9.583844911147012e-06,
|
| 140284 |
+
"loss": 0.5289,
|
| 140285 |
+
"step": 26770
|
| 140286 |
+
},
|
| 140287 |
+
{
|
| 140288 |
+
"epoch": 215.24,
|
| 140289 |
+
"learning_rate": 9.583683360258482e-06,
|
| 140290 |
+
"loss": 1.069,
|
| 140291 |
+
"step": 26780
|
| 140292 |
+
},
|
| 140293 |
+
{
|
| 140294 |
+
"epoch": 215.32,
|
| 140295 |
+
"learning_rate": 9.583521809369952e-06,
|
| 140296 |
+
"loss": 0.4077,
|
| 140297 |
+
"step": 26790
|
| 140298 |
+
},
|
| 140299 |
+
{
|
| 140300 |
+
"epoch": 215.4,
|
| 140301 |
+
"learning_rate": 9.583360258481422e-06,
|
| 140302 |
+
"loss": 1.0294,
|
| 140303 |
+
"step": 26800
|
| 140304 |
+
},
|
| 140305 |
+
{
|
| 140306 |
+
"epoch": 215.48,
|
| 140307 |
+
"learning_rate": 9.583198707592892e-06,
|
| 140308 |
+
"loss": 0.4299,
|
| 140309 |
+
"step": 26810
|
| 140310 |
+
},
|
| 140311 |
+
{
|
| 140312 |
+
"epoch": 215.56,
|
| 140313 |
+
"learning_rate": 9.583037156704362e-06,
|
| 140314 |
+
"loss": 0.5385,
|
| 140315 |
+
"step": 26820
|
| 140316 |
+
},
|
| 140317 |
+
{
|
| 140318 |
+
"epoch": 215.64,
|
| 140319 |
+
"learning_rate": 9.582875605815832e-06,
|
| 140320 |
+
"loss": 1.0213,
|
| 140321 |
+
"step": 26830
|
| 140322 |
+
},
|
| 140323 |
+
{
|
| 140324 |
+
"epoch": 215.72,
|
| 140325 |
+
"learning_rate": 9.582714054927302e-06,
|
| 140326 |
+
"loss": 0.413,
|
| 140327 |
+
"step": 26840
|
| 140328 |
+
},
|
| 140329 |
+
{
|
| 140330 |
+
"epoch": 215.8,
|
| 140331 |
+
"learning_rate": 9.582552504038774e-06,
|
| 140332 |
+
"loss": 1.042,
|
| 140333 |
+
"step": 26850
|
| 140334 |
+
},
|
| 140335 |
+
{
|
| 140336 |
+
"epoch": 215.88,
|
| 140337 |
+
"learning_rate": 9.582390953150244e-06,
|
| 140338 |
+
"loss": 0.3795,
|
| 140339 |
+
"step": 26860
|
| 140340 |
+
},
|
| 140341 |
+
{
|
| 140342 |
+
"epoch": 215.96,
|
| 140343 |
+
"learning_rate": 9.582229402261714e-06,
|
| 140344 |
+
"loss": 0.5328,
|
| 140345 |
+
"step": 26870
|
| 140346 |
+
},
|
| 140347 |
+
{
|
| 140348 |
+
"epoch": 216.0,
|
| 140349 |
+
"eval_loss": 0.5103784799575806,
|
| 140350 |
+
"eval_runtime": 42.0953,
|
| 140351 |
+
"eval_samples_per_second": 20.074,
|
| 140352 |
+
"eval_steps_per_second": 0.641,
|
| 140353 |
+
"eval_wer": 0.2350846595450912,
|
| 140354 |
+
"step": 26874
|
| 140355 |
+
},
|
| 140356 |
+
{
|
| 140357 |
+
"epoch": 214.05,
|
| 140358 |
+
"learning_rate": 9.582067851373184e-06,
|
| 140359 |
+
"loss": 0.4642,
|
| 140360 |
+
"step": 26880
|
| 140361 |
+
},
|
| 140362 |
+
{
|
| 140363 |
+
"epoch": 214.13,
|
| 140364 |
+
"learning_rate": 9.581906300484654e-06,
|
| 140365 |
+
"loss": 0.4359,
|
| 140366 |
+
"step": 26890
|
| 140367 |
+
},
|
| 140368 |
+
{
|
| 140369 |
+
"epoch": 214.21,
|
| 140370 |
+
"learning_rate": 9.581744749596124e-06,
|
| 140371 |
+
"loss": 1.0707,
|
| 140372 |
+
"step": 26900
|
| 140373 |
+
},
|
| 140374 |
+
{
|
| 140375 |
+
"epoch": 214.29,
|
| 140376 |
+
"learning_rate": 9.581583198707594e-06,
|
| 140377 |
+
"loss": 0.4818,
|
| 140378 |
+
"step": 26910
|
| 140379 |
+
},
|
| 140380 |
+
{
|
| 140381 |
+
"epoch": 214.37,
|
| 140382 |
+
"learning_rate": 9.581421647819064e-06,
|
| 140383 |
+
"loss": 0.6132,
|
| 140384 |
+
"step": 26920
|
| 140385 |
+
},
|
| 140386 |
+
{
|
| 140387 |
+
"epoch": 214.45,
|
| 140388 |
+
"learning_rate": 9.581260096930534e-06,
|
| 140389 |
+
"loss": 0.9304,
|
| 140390 |
+
"step": 26930
|
| 140391 |
+
},
|
| 140392 |
+
{
|
| 140393 |
+
"epoch": 214.53,
|
| 140394 |
+
"learning_rate": 9.581098546042004e-06,
|
| 140395 |
+
"loss": 0.4587,
|
| 140396 |
+
"step": 26940
|
| 140397 |
+
},
|
| 140398 |
+
{
|
| 140399 |
+
"epoch": 214.61,
|
| 140400 |
+
"learning_rate": 9.580936995153474e-06,
|
| 140401 |
+
"loss": 0.9559,
|
| 140402 |
+
"step": 26950
|
| 140403 |
+
},
|
| 140404 |
+
{
|
| 140405 |
+
"epoch": 214.69,
|
| 140406 |
+
"learning_rate": 9.580775444264945e-06,
|
| 140407 |
+
"loss": 0.4159,
|
| 140408 |
+
"step": 26960
|
| 140409 |
+
},
|
| 140410 |
+
{
|
| 140411 |
+
"epoch": 214.77,
|
| 140412 |
+
"learning_rate": 9.580613893376415e-06,
|
| 140413 |
+
"loss": 0.5743,
|
| 140414 |
+
"step": 26970
|
| 140415 |
+
},
|
| 140416 |
+
{
|
| 140417 |
+
"epoch": 214.85,
|
| 140418 |
+
"learning_rate": 9.580452342487885e-06,
|
| 140419 |
+
"loss": 0.8485,
|
| 140420 |
+
"step": 26980
|
| 140421 |
+
},
|
| 140422 |
+
{
|
| 140423 |
+
"epoch": 214.93,
|
| 140424 |
+
"learning_rate": 9.580290791599355e-06,
|
| 140425 |
+
"loss": 0.4244,
|
| 140426 |
+
"step": 26990
|
| 140427 |
+
},
|
| 140428 |
+
{
|
| 140429 |
+
"epoch": 215.0,
|
| 140430 |
+
"eval_loss": 0.4798107445240021,
|
| 140431 |
+
"eval_runtime": 38.9644,
|
| 140432 |
+
"eval_samples_per_second": 21.558,
|
| 140433 |
+
"eval_steps_per_second": 0.693,
|
| 140434 |
+
"eval_wer": 0.2277842736042093,
|
| 140435 |
+
"step": 26999
|
| 140436 |
}
|
| 140437 |
],
|
| 140438 |
+
"max_steps": 625000,
|
| 140439 |
"num_train_epochs": 5000,
|
| 140440 |
+
"total_flos": 7.597350515285315e+19,
|
| 140441 |
"trial_name": null,
|
| 140442 |
"trial_params": null
|
| 140443 |
}
|
model-bin/finetune/base/{checkpoint-26377 → checkpoint-26999}/training_args.bin
RENAMED
|
File without changes
|
model-bin/finetune/base/log/1629611321.118057/events.out.tfevents.1629611321.91f414e9573a.903.61
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91bd308bc96bf820bac9cb54bc0b7249598128f60aff791ea1463e417a7b1a71
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629611966.8683221/events.out.tfevents.1629611966.91f414e9573a.903.63
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27c23319d2f19a5d4d43649ca2ea8b850313132ad0d36a52dfc1a095512a81c3
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629612621.1430087/events.out.tfevents.1629612621.91f414e9573a.903.65
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea907d9b9cd087bb13ccab990144ab88283bc1b2d1e1223a27aafafcd4849347
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629613282.6240292/events.out.tfevents.1629613282.91f414e9573a.903.67
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43427d256b92e5887600a9bd14575a068d5155438da9327071ce794072afc25b
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629614041.3431811/events.out.tfevents.1629614041.91f414e9573a.903.69
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbf81ea1c94d41c3ccdb606fe6f8688275c61a0f5e2e9cf3cfde0b50458fe8eb
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/events.out.tfevents.1629611321.91f414e9573a.903.60
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bbbb2f95056afe1ce78468dad2e7776e12977c726233bee0434c81a48e36bd77
|
| 3 |
+
size 6703
|
model-bin/finetune/base/log/events.out.tfevents.1629611966.91f414e9573a.903.62
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb329b87ba0637a957e77b20ce4f83fd9a97cc23ff663a31677012be387061a5
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629612621.91f414e9573a.903.64
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:470589e4e41f13ab0906890da99bef9d1f1e669dc1e26997c11e138c67f80359
|
| 3 |
+
size 6703
|
model-bin/finetune/base/log/events.out.tfevents.1629613282.91f414e9573a.903.66
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f19ba97d0582efe5373de56f539ec31e4d22b72b919084369b403cfcf6f25763
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629614041.91f414e9573a.903.68
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2de873fe14cb6fba599df1029cb31b7f291cc26487833cccffe37d357b05121
|
| 3 |
+
size 6543
|